Author name cluster

Yuanyu Wan

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

30 papers

2 author rows

AAAI Conference 2026 Conference Paper

Beyond the Lower Bound: Bridging Regret Minimization and Best Arm Identification in Lexicographic Bandits

Bo Xue
Yuanyu Wan
Zhichao Lu
Qingfu Zhang

In multi-objective decision-making with hierarchical preferences, lexicographic bandits provide a natural framework for optimizing multiple objectives in a prioritized order. In this setting, a learner repeatedly selects arms and observes reward vectors, aiming to maximize the reward for the highest-priority objective, then the next, and so on. While previous studies have primarily focused on regret minimization, this work bridges the gap between regret minimization and best arm identification under lexicographic preferences. We propose two elimination-based algorithms to address this joint objective. The first algorithm eliminates suboptimal arms sequentially, layer by layer, in accordance with the objective priorities, and achieves sample complexity and regret bounds comparable to those of the best single-objective algorithms. The second algorithm simultaneously leverages reward information from all objectives in each round, effectively exploiting cross-objective dependencies. Remarkably, it outperforms the known lower bound for the single-objective bandit problem, highlighting the benefit of cross-objective information sharing in the multi-objective setting. Empirical results further validate their superior performance over baselines.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Continuous Subspace Optimization for Continual Learning

Quan Cheng
Yuanyu Wan
Lingyu Wu
Chenping Hou
Lijun Zhang

Continual learning aims to learn multiple tasks sequentially while preserving prior knowledge, but faces the challenge of catastrophic forgetting when adapting to new tasks. Recently, approaches leveraging pre-trained models have gained increasing popularity in mitigating this issue, due to the strong generalization ability of foundation models. To adjust pre-trained models for new tasks, existing methods usually employ low-rank adaptation, which restricts parameter updates to a fixed low-rank subspace. However, constraining the optimization space inherently compromises the model's learning capacity, resulting in inferior performance. To address this limitation, we propose Continuous Subspace Optimization for Continual Learning (CoSO) to fine-tune the model in a series of subspaces rather than a single one. These sequential subspaces are dynamically determined through the singular value decomposition of the gradients. CoSO updates the model by projecting gradients onto these subspaces, ensuring memory-efficient optimization. To mitigate forgetting, the optimization subspace of each task is constrained to be orthogonal to the historical task subspace. During task learning, CoSO maintains a task-specific component that captures the critical update directions for the current task. Upon completing a task, this component is used to update the historical task subspace, laying the groundwork for subsequent learning. Extensive experiments on multiple datasets demonstrate that CoSO significantly outperforms state-of-the-art methods, especially in challenging scenarios with long task sequences.

PDF Details

ICML Conference 2025 Conference Paper

Dimension-Free Adaptive Subgradient Methods with Frequent Directions

Sifan Yang
Yuanyu Wan
Peijia Li
Yibo Wang 0005
Xiao Zhang
Zhewei Wei
Lijun Zhang 0005

In this paper, we investigate the acceleration of adaptive subgradient methods through frequent directions (FD), a widely-used matrix sketching technique. The state-of-the-art regret bound exhibits a linear dependence on the dimensionality $d$, leading to unsatisfactory guarantees for high-dimensional problems. Additionally, it suffers from an $O(\tau^2 d)$ time complexity per round, which scales quadratically with the sketching size $\tau$. To overcome these issues, we first propose an algorithm named FTSL, achieving a tighter regret bound that is independent of the dimensionality. The key idea is to integrate FD with adaptive subgradient methods under the primal-dual framework and add the cumulative discarded information of FD back. To reduce its time complexity, we further utilize fast FD to expedite FTSL, yielding a better complexity of $O(\tau d)$ while maintaining the same regret bound. Moreover, to mitigate the computational cost for optimization problems involving matrix variables (e. g. , training neural networks), we adapt FD to Shampoo, a popular optimization algorithm that accounts for the structure of decision, and give a novel analysis under the primal-dual framework. Our proposed method obtains an improved dimension-free regret bound. Experimental results have verified the efficiency and effectiveness of our approaches.

Details

AAAI Conference 2025 Conference Paper

Mixture of Online and Offline Experts for Non-Stationary Time Series

Zhilin Zhao
Longbing Cao
Yuanyu Wan

We consider a general and realistic scenario involving non-stationary time series, consisting of several offline intervals with different distributions within a fixed offline time horizon, and an online interval that continuously receives new samples. For non-stationary time series, the data distribution in the current online interval may have appeared in previous offline intervals. We theoretically explore the feasibility of applying knowledge from offline intervals to the current online interval. To this end, we propose the Mixture of Online and Offline Experts (MOOE). MOOE learns static offline experts from offline intervals and maintains a dynamic online expert for the current online interval. It then adaptively combines the offline and online experts using a meta expert to make predictions for the samples received in the online interval. Specifically, we focus on theoretical analysis, deriving parameter convergence, regret bounds, and generalization error bounds to prove the effectiveness of the algorithm.

PDF Details DOI

ICML Conference 2025 Conference Paper

Multi-objective Linear Reinforcement Learning with Lexicographic Rewards

Bo Xue 0004
Dake Bu
Ji Cheng 0001
Yuanyu Wan
Qingfu Zhang 0001

Reinforcement Learning (RL) with linear transition kernels and reward functions has recently attracted growing attention due to its computational efficiency and theoretical advancements. However, prior theoretical research in RL has primarily focused on single-objective problems, resulting in limited theoretical development for multi-objective reinforcement learning (MORL). To bridge this gap, we examine MORL under lexicographic reward structures, where rewards comprise $m$ hierarchically ordered objectives. In this framework, the agent the agent maximizes objectives sequentially, prioritizing the highest-priority objective before considering subsequent ones. We introduce the first MORL algorithm with provable regret guarantees. For any objective $i \in \\{1, 2, \ldots, m\\}$, our algorithm achieves a regret bound of $\widetilde{O}(\Lambda^i(\lambda) \cdot \sqrt{d^2H^4 K})$, where $\Lambda^i(\lambda) = 1 + \lambda + \cdots + \lambda^{i-1}$, $\lambda$ quantifies the trade-off between conflicting objectives, $d$ is the feature dimension, $H$ is the episode length, and $K$ is the number of episodes. Furthermore, our algorithm can be applied in the misspecified setting, where the regret bound for the $i$-th objective becomes $\widetilde{O}(\Lambda^i(\lambda)\cdot(\sqrt{d^2H^4K}+\epsilon dH^2K))$, with $\epsilon$ denoting the degree of misspecification.

Details

AAAI Conference 2025 Conference Paper

Online Nonsubmodular Optimization with Delayed Feedback in the Bandit Setting

Sifan Yang
Yuanyu Wan
Lijun Zhang

We investigate the online nonsubmodular optimization with delayed feedback in the bandit setting, where the loss function is α-weakly DR-submodular and β-weakly DR-supermodular. Previous work has established an (α,β)-regret bound of O(nd^⅓T^⅔), where n is the dimensionality and d is the maximum delay. However, its regret bound relies on the maximum delay and is thus sensitive to irregular delays. Additionally, it couples the effects of delays and bandit feedback as its bound is the product of the delay term and the O(nT^⅔) regret bound in the bandit setting without delayed feedback. In this paper, we develop two algorithms to address these limitations, respectively. Firstly, we propose a novel method, namely DBGD-NF, which employs the one-point gradient estimator and utilizes all the available estimated gradients in each round to update the decision. It achieves a better O(nd̅^⅓T^⅔) regret bound, which is relevant to the average delay d̅ = 1/T ∑ₜ₌₁ᵀ dₜ <= d. Secondly, we extend DBGD-NF by employing a blocking update mechanism to decouple the joint effect of the delays and bandit feedback, which enjoys an O(n(T^⅔+ √(dT))) regret bound. When d = O(T^⅓), our regret bound matches the O(nT^⅔) bound in the bandit setting without delayed feedback. Compared to our first O(nd̅^⅓T^⅔) bound, it is more advantageous when the maximum delay d = o(d̅^⅔T^⅓). Finally, we conduct experiments on structured sparse learning to demonstrate the superiority of our methods.

PDF Details DOI

JMLR Journal 2025 Journal Article

Optimal and Efficient Algorithms for Decentralized Online Convex Optimization

Yuanyu Wan
Tong Wei
Bo Xue
Mingli Song
Lijun Zhang

We investigate decentralized online convex optimization (D-OCO), in which a set of local learners are required to minimize a sequence of global loss functions using only local computations and communications. Previous studies have established $O(n^{5/4}\rho^{-1/2}\sqrt{T})$ and ${O}(n^{3/2}\rho^{-1}\log T)$ regret bounds for convex and strongly convex functions respectively, where $n$ is the number of local learners, $\rho [abs] [ pdf ][ bib ] &copy JMLR 2025. ( edit, beta )

PDF Details

IJCAI Conference 2025 Conference Paper

Problem-dependent Regret for Lexicographic Multi-Armed Bandits with Adversarial Corruptions

Bo Xue
Xi Lin
Yuanyu Wan
Qingfu Zhang

This paper studies lexicographic multi-armed bandits (MAB), where after selecting an arm, the agent observes a reward vector including multiple objectives, each with a different level of importance. Although previous literature has proposed the algorithm for lexicographic MAB, their algorithm suffers from several limitations: (1) it exhibits poor adversarial robustness due to its reliance on stochastic rewards, (2) its regret bound is suboptimal compared to single-objective counterparts, and (3) the regret bound does not adapt to specific problem instances. To address these limitations, we study lexicographic MAB with adversarial corruptions, where an adversary might corrupt the stochastic rewards with a corruption budget of C. First, when the value of C is known, we propose an algorithm achieving a problem-dependent regret bound of O(∑(log T / Δⁱ(a) + C)) for the i-th objective (i ∈ [M]), where Δⁱ(a) is the reward gap for arm a on the i-th objective, and M is the number of objectives. In the purely stochastic setting (C=0), this regret bound approaches optimality. Second, we introduce another algorithm that does not require value of C but incurs a less favorable regret bound of O(∑(γ_T / Δⁱ(a) + γ_T)) for the i-th objective, where γ_T = O((log T)² + KC(log T)²). Finally, we conduct experiments on both synthetic and real-world datasets to verify the effectiveness of our algorithms.

PDF Details DOI

ICML Conference 2025 Conference Paper

Revisiting Differentially Private Algorithms for Decentralized Online Learning

Xiaoyu Wang
Wenhao Yang
Chang Yao 0001
Mingli Song
Yuanyu Wan

Although the differential privacy (DP) of decentralized online learning has garnered considerable attention recently, existing algorithms are unsatisfactory due to their inability to achieve $(\epsilon, 0)$-DP over all $T$ rounds, recover the optimal regret in the non-private case, and maintain the lightweight computation under complex constraints. To address these issues, we first propose a new decentralized online learning algorithm satisfying $(\epsilon, 0)$-DP over $T$ rounds, and show that it can achieve $\widetilde{O}(n(\rho^{-1/4}+\epsilon^{-1}\rho^{1/4})\sqrt{T})$ and $\widetilde{O}(n (\rho^{-1/2}+\epsilon^{-1}))$ regret bounds for convex and strongly convex functions respectively, where $n$ is the number of local learners and $\rho$ is the spectral gap of the communication matrix. As long as $\epsilon=\Omega(\sqrt{\rho})$, these bounds nearly match existing lower bounds in the non-private case, which implies that $(\epsilon, 0)$-DP of decentralized online learning may be ensured nearly for free. Our key idea is to design a block-decoupled accelerated gossip strategy that can be incorporated with the classical tree-based private aggregation, and also enjoys a faster average consensus among local learners. Furthermore, we develop a projection-free variant of our algorithm to keep the efficiency under complex constraints. As a trade-off, the above regret bounds degrade to $\widetilde{O}(n(T^{3/4}+\epsilon^{-1}T^{1/4}))$ and $\widetilde{O}(n(T^{2/3}+\epsilon^{-1}))$ respectively, which however are even better than the existing private centralized projection-free online algorithm.

Details

AAAI Conference 2025 Conference Paper

Revisiting Projection-Free Online Learning with Time-Varying Constraints

Yibo Wang
Yuanyu Wan
Lijun Zhang

We investigate constrained online convex optimization, in which decisions must belong to a fixed and typically complicated domain, and are required to approximately satisfy additional time-varying constraints over the long term. In this setting, the commonly used projection operations are often computationally expensive or even intractable. To avoid the time-consuming operation, several projection-free methods have been proposed with an O(T^¾ (log T)^½) regret bound and an O(T^⅞) cumulative constraint violation (CCV) bound for general convex losses. In this paper, we improve this result and further establish novel regret and CCV bounds when loss functions are strongly convex. The primary idea is to first construct a composite surrogate loss, involving the original loss and constraint functions, by utilizing the Lyapunov-based technique. Then, we propose a parameter-free variant of the classical projection-free method, namely online Frank-Wolfe (OFW), and run this new extension over the online-generated surrogate loss. Theoretically, for general convex losses, we achieve an O(T^¾) regret bound and an O(T^¾ log T) CCV bound, both of which are order-wise tighter than existing results. For strongly convex losses, we establish new guarantees of an O(T^⅔) regret bound and an O(T^⅚) CCV bound. Moreover, we also extend our methods to a more challenging setting with bandit feedback, obtaining similar theoretical findings. Empirically, experiments on real-world datasets have demonstrated the effectiveness of our methods.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Safe Online Convex Optimization with Heavy-Tailed Observation Noises

Yunhao Yang
Bo Xue
Yunzhi Hao
Ying Li
Yuanyu Wan

We investigate safe online convex optimization (SOCO), where each decision must satisfy a set of unknown linear constraints. Assuming that the unknown constraints can be observed with a sub-Gaussian noise for each chosen decision, previous studies have established a high-probability regret bound of O(T^{2/3}). However, this assumption may not hold in many practical scenarios. To address this limitation, in this paper, we relax the assumption to allow any noise that admits finite (1+ε)-th moments for some ε∈(0,1], and propose two algorithms that enjoy an O(T^{c_ε}) regret bound with high probability, where T is the time horizon and c_ε=(1+ε)/(1+2ε). The key idea of our two algorithms is to respectively utilize the median-of-means and truncation techniques to achieve accurate estimation under heavy-tailed noises. To the best of our knowledge, these are the first algorithms designed to handle SOCO with heavy-tailed observation noises.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

Smoothed Online Convex Optimization with Delayed Feedback

Sifan Yang
Wenhao Yang
Wei Jiang
Yuanyu Wan
Lijun Zhang

Smoothed online convex optimization (SOCO), in which the online player incurs both a hitting cost and a switching cost for changing its decisions, has garnered significant attention in recent years. While existing studies typically assume that the gradient information is revealed immediately, such an assumption may not hold in some real-world applications. To overcome this limitation, we investigate SOCO with delayed feedback, and develop two online algorithms that can minimize the dynamic regret with switching cost. Firstly, we extend Mild-OGD, an existing algorithm that adopts the meta-expert framework for online convex optimization with delayed feedback, to account for switching cost. Specifically, we analyze the switching cost in the expert-algorithm of Mild-OGD, and then modify its meta-algorithm to incorporate this cost when assigning the weight to each expert. We demonstrate that our proposed method, Smelt-DOGD can achieve an O(√(dT(P_T+1))) dynamic regret bound with switching cost, where d is the maximum delay and P_T is the path-length. Secondly, we develop an efficient variant to reduce the number of projections per round from O(log T) to 1, yet maintaining the same theoretical guarantee. The key idea is to construct a new surrogate loss defined over a simpler domain for expert-algorithms so that these experts do not need to perform the complex projection operations in each round. Finally, we conduct experiments to validate the effectiveness and efficiency of our algorithms.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition

Zi-Hao Zhou
Siyuan Fang
Zi-Jing Zhou
Tong Wei
Yuanyu Wan
Min-Ling Zhang

Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-art LTSSL approaches heavily rely on high-quality pseudo-labels for large-scale unlabeled data. However, these methods often neglect the impact of representations learned by the neural network and struggle with real-world unlabeled data, which typically follows a different distribution than labeled data. This paper introduces a novel probabilistic framework that unifies various recent proposals in long-tail learning. Our framework derives the class-balanced contrastive loss through Gaussian kernel density estimation. We introduce a continuous contrastive learning method, CCL, extending our framework to unlabeled data using reliable and smoothed pseudo-labels. By progressively estimating the underlying label distribution and optimizing its alignment with model predictions, we tackle the diverse distribution of unlabeled data in real-world scenarios. Extensive experiments across multiple datasets with varying unlabeled data distributions demonstrate that CCL consistently outperforms prior state-of-the-art methods, achieving over 4% improvement on the ImageNet-127 dataset. The supplementary material includes the source code for reproducibility.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Improved Regret for Bandit Convex Optimization with Delayed Feedback

Yuanyu Wan
Chang Yao
Mingli Song
Lijun Zhang

We investigate bandit convex optimization (BCO) with delayed feedback, where only the loss value of the action is revealed under an arbitrary delay. Let $n, T, \bar{d}$ denote the dimensionality, time horizon, and average delay, respectively. Previous studies have achieved an $O(\sqrt{n}T^{3/4}+(n\bar{d})^{1/3}T^{2/3})$ regret bound for this problem, whose delay-independent part matches the regret of the classical non-delayed bandit gradient descent algorithm. However, there is a large gap between its delay-dependent part, i. e. , $O((n\bar{d})^{1/3}T^{2/3})$, and an existing $\Omega(\sqrt{\bar{d}T})$ lower bound. In this paper, we illustrate that this gap can be filled in the worst case, where $\bar{d}$ is very close to the maximum delay $d$. Specifically, we first develop a novel algorithm, and prove that it enjoys a regret bound of $O(\sqrt{n}T^{3/4}+\sqrt{dT})$ in general. Compared with the previous result, our regret bound is better for $d=O((n\bar{d})^{2/3}T^{1/3})$, and the delay-dependent part is tight in the worst case. The primary idea is to decouple the joint effect of the delays and the bandit feedback on the regret by carefully incorporating the delayed bandit feedback with a blocking update mechanism. Furthermore, we show that the proposed algorithm can improve the regret bound to $O((nT)^{2/3}\log^{1/3}T+d\log T)$ for strongly convex functions. Finally, if the action sets are unconstrained, we demonstrate that it can be simply extended to achieve an $O(n\sqrt{T\log T}+d\log T)$ regret bound for strongly convex and smooth functions.

PDF Details DOI

ICML Conference 2024 Conference Paper

Learning Label Shift Correction for Test-Agnostic Long-Tailed Recognition

Tong Wei 0001
Zhen Mao
Zi-Hao Zhou
Yuanyu Wan
Min-Ling Zhang

Long-tail learning primarily focuses on mitigating the label distribution shift between long-tailed training data and uniformly distributed test data. However, in real-world applications, we often encounter a more intricate challenge where the test label distribution is agnostic. To address this problem, we first theoretically establish the substantial potential for reducing the generalization error if we can precisely estimate the test label distribution. Motivated by the theoretical insight, we introduce a simple yet effective solution called label shift correction (LSC). LSC estimates the test label distribution within the proposed framework of generalized black box shift estimation, and adjusts the predictions from a pre-trained model to align with the test distribution. Theoretical analyses confirm that accurate estimation of test label distribution can effectively reduce the generalization error. Extensive experimental results demonstrate that our method significantly outperforms previous state-of-the-art approaches, especially when confronted with non-uniform test label distribution. Notably, the proposed method is general and complements existing long-tail learning approaches, consistently improving their performance. The source code is available at https: //github. com/Stomach-ache/label-shift-correction

Details

ICML Conference 2024 Conference Paper

Non-stationary Online Convex Optimization with Arbitrary Delays

Yuanyu Wan
Chang Yao 0001
Mingli Song
Lijun Zhang 0005

Online convex optimization (OCO) with arbitrary delays, in which gradients or other information of functions could be arbitrarily delayed, has received increasing attention recently. Different from previous studies that focus on stationary environments, this paper investigates the delayed OCO in non-stationary environments, and aims to minimize the dynamic regret with respect to any sequence of comparators. To this end, we first propose a simple algorithm, namely DOGD, which performs a gradient descent step for each delayed gradient according to their arrival order. Despite its simplicity, our novel analysis shows that the dynamic regret of DOGD can be automatically bounded by $O(\sqrt{\bar{d}T}(P_T+1))$ under mild assumptions, and $O(\sqrt{dT}(P_T+1))$ in the worst case, where $\bar{d}$ and $d$ denote the average and maximum delay respectively, $T$ is the time horizon, and $P_T$ is the path-length of comparators. Furthermore, we develop an improved algorithm, which reduces those dynamic regret bounds achieved by DOGD to $O(\sqrt{\bar{d}T(P_T+1)})$ and $O(\sqrt{dT(P_T+1)})$, respectively. The key idea is to run multiple DOGD with different learning rates, and utilize a meta-algorithm to track the best one based on their delayed performance. Finally, we demonstrate that our improved algorithm is optimal in the worst case by deriving a matching lower bound.

Details

AAAI Conference 2024 Conference Paper

Non-stationary Projection-Free Online Learning with Dynamic and Adaptive Regret Guarantees

Yibo Wang
Wenhao Yang
Wei Jiang
Shiyin Lu
Bing Wang
Haihong Tang
Yuanyu Wan
Lijun Zhang

Projection-free online learning has drawn increasing interest due to its efficiency in solving high-dimensional problems with complicated constraints. However, most existing projection-free online methods focus on minimizing the static regret, which unfortunately fails to capture the challenge of changing environments. In this paper, we investigate non-stationary projection-free online learning, and choose dynamic regret and adaptive regret to measure the performance. Specifically, we first provide a novel dynamic regret analysis for an existing projection-free method named BOGD_IP, and establish an O(T^¾ (1+P_T)) dynamic regret bound, where P_T denotes the path-length of the comparator sequence. Then, we improve the upper bound to O(T^¾ (1+P_T)^¼) by running multiple BOGD_IP algorithms with different step sizes in parallel, and tracking the best one on the fly. Our results are the first general-case dynamic regret bounds for projection-free online learning, and can recover the existing O(T^¾) static regret by setting P_T = 0. Furthermore, we propose a projection-free method to attain an O(?^¾) adaptive regret bound for any interval with length?, which nearly matches the static regret over that interval. The essential idea is to maintain a set of BOGD_IP algorithms dynamically, and combine them by a meta algorithm. Moreover, we demonstrate that it is also equipped with an O(T^¾ (1+P_T)^¼) dynamic regret bound. Finally, empirical studies verify our theoretical findings.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Online Composite Optimization Between Stochastic and Adversarial Environments

Yibo Wang
Sijia Chen
Wei Jiang
Wenhao Yang
Yuanyu Wan
Lijun Zhang

We study online composite optimization under the Stochastically Extended Adversarial (SEA) model. Specifically, each loss function consists of two parts: a fixed non-smooth and convex regularizer, and a time-varying function which can be chosen either stochastically, adversarially, or in a manner that interpolates between the two extremes. In this setting, we show that for smooth and convex time-varying functions, optimistic composite mirror descent (OptCMD) can obtain an $\mathcal{O}(\sqrt{\sigma_{1: T}^2} + \sqrt{\Sigma_{1: T}^2})$ regret bound, where $\sigma_{1: T}^2$ and $\Sigma_{1: T}^2$ denote the cumulative stochastic variance and the cumulative adversarial variation of time-varying functions, respectively. For smooth and strongly convex time-varying functions, we establish an $\mathcal{O}((\sigma_{\max}^2 + \Sigma_{\max}^2)\log(\sigma_{1: T}^2 + \Sigma_{1: T}^2))$ regret bound, where $\sigma_{\max}^2$ and $\Sigma_{\max}^2$ denote the maximal stochastic variance and the maximal adversarial variation, respectively. For smooth and exp-concave time-varying functions, we achieve an $\mathcal{O}(d \log (\sigma_{1: T}^2 + \Sigma_{1: T}^2))$ bound where $d$ denotes the dimensionality. Moreover, to deal with the unknown function type in practical problems, we propose a multi-level \textit{universal} algorithm that is able to achieve the desirable bounds for three types of time-varying functions simultaneously. It should be noticed that all our findings match existing bounds for the SEA model without the regularizer, which implies that there is \textit{no price} in regret bounds for the benefits gained from the regularizer.

PDF Details DOI

ICML Conference 2024 Conference Paper

Projection-Free Variance Reduction Methods for Stochastic Constrained Multi-Level Compositional Optimization

Wei Jiang 0029
Sifan Yang
Wenhao Yang
Yibo Wang 0005
Yuanyu Wan
Lijun Zhang 0005

This paper investigates projection-free algorithms for stochastic constrained multi-level optimization. In this context, the objective function is a nested composition of several smooth functions, and the decision set is closed and convex. Existing projection-free algorithms for solving this problem suffer from two limitations: 1) they solely focus on the gradient mapping criterion and fail to match the optimal sample complexities in unconstrained settings; 2) their analysis is exclusively applicable to non-convex functions, without considering convex and strongly convex objectives. To address these issues, we introduce novel projection-free variance reduction algorithms and analyze their complexities under different criteria. For gradient mapping, our complexities improve existing results and match the optimal rates for unconstrained problems. For the widely-used Frank-Wolfe gap criterion, we provide theoretical guarantees that align with those for single-level problems. Additionally, by using a stage-wise adaptation, we further obtain complexities for convex and strongly convex functions. Finally, numerical experiments on different tasks demonstrate the effectiveness of our methods.

Details

ECAI Conference 2023 Conference Paper

Adversarial Erasing with Pruned Elements: Towards Better Graph Lottery Tickets

Yuwen Wang
Shunyu Liu 0001
Kaixuan Chen 0004
Tongtian Zhu
Ji Qiao
Mengjie Shi
Yuanyu Wan
Mingli Song

Graph Lottery Ticket (GLT), a combination of core subgraph and sparse subnetwork, has been proposed to mitigate the computational cost of deep Graph Neural Networks (GNNs) on large input graphs while preserving original performance. However, the winning GLTs in exisiting studies are obtained by applying iterative magnitude-based pruning (IMP) without re-evaluating and re-considering the pruned information, which disregards the dynamic changes in the significance of edges/weights during graph/model structure pruning, and thus limits the appeal of the winning tickets. In this paper, we formulate a conjecture, i. e. , existing overlooked valuable information in the pruned graph connections and model parameters which can be re-grouped into GLT to enhance the final performance. Specifically, we propose an adversarial complementary erasing (ACE) framework to explore the valuable information from the pruned components, thereby developing a more powerful GLT, referred to as the ACE-GLT. The main idea is to mine valuable information from pruned edges/weights after each round of IMP, and employ the ACE technique to refine the GLT processing. Finally, experimental results demonstrate that our ACE-GLT outperforms existing methods for searching GLT in diverse tasks. Our code is available at https: //github. com/Wangyuwen0627/ACE-GLT.

Details

AAAI Conference 2023 Conference Paper

Distributed Projection-Free Online Learning for Smooth and Convex Losses

Yibo Wang
Yuanyu Wan
Shimao Zhang
Lijun Zhang

We investigate the problem of distributed online convex optimization with complicated constraints, in which the projection operation could be the computational bottleneck. To avoid projections, distributed online projection-free methods have been proposed and attain an O(T^{3/4}) regret bound for general convex losses. However, they cannot utilize the smoothness condition, which has been exploited in the centralized setting to improve the regret. In this paper, we propose a new distributed online projection-free method with a tighter regret bound of O(T^{2/3}) for smooth and convex losses. Specifically, we first provide a distributed extension of Follow-the-Perturbed-Leader so that the smoothness can be utilized in the distributed setting. Then, we reduce the computational cost via sampling and blocking techniques. In this way, our method only needs to solve one linear optimization per round on average. Finally, we conduct experiments on benchmark datasets to verify the effectiveness of our proposed method.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Efficient Algorithms for Generalized Linear Bandits with Heavy-tailed Rewards

Bo Xue
Yimu Wang
Yuanyu Wan
Jinfeng Yi
Lijun Zhang

This paper investigates the problem of generalized linear bandits with heavy-tailed rewards, whose $(1+\epsilon)$-th moment is bounded for some $\epsilon\in (0, 1]$. Although there exist methods for generalized linear bandits, most of them focus on bounded or sub-Gaussian rewards and are not well-suited for many real-world scenarios, such as financial markets and web-advertising. To address this issue, we propose two novel algorithms based on truncation and mean of medians. These algorithms achieve an almost optimal regret bound of $\widetilde{O}(dT^{\frac{1}{1+\epsilon}})$, where $d$ is the dimension of contextual information and $T$ is the time horizon. Our truncation-based algorithm supports online learning, distinguishing it from existing truncation-based approaches. Additionally, our mean-of-medians-based algorithm requires only $O(\log T)$ rewards and one estimator per epoch, making it more practical. Moreover, our algorithms improve the regret bounds by a logarithmic factor compared to existing algorithms when $\epsilon=1$. Numerical experimental results confirm the merits of our algorithms.

PDF Details

NeurIPS Conference 2022 Conference Paper

Online Frank-Wolfe with Arbitrary Delays

Yuanyu Wan
Wei-Wei Tu
Lijun Zhang

The online Frank-Wolfe (OFW) method has gained much popularity for online convex optimization due to its projection-free property. Previous studies show that OFW can attain an $O(T^{3/4})$ regret bound for convex losses and an $O(T^{2/3})$ regret bound for strongly convex losses. However, they assume that each gradient queried by OFW is revealed immediately, which may not hold in practice and limits the application of OFW. To address this limitation, we propose a delayed variant of OFW, which allows gradients to be delayed by arbitrary rounds. The main idea is to perform an update similar to OFW after receiving any delayed gradient, and play the latest decision for each round. Despite its simplicity, we prove that our delayed variant of OFW is able to achieve an $O(T^{3/4}+dT^{1/4})$ regret bound for convex losses and an $O(T^{2/3}+d\log T)$ regret bound for strongly convex losses, where $d$ is the maximum delay. This is quite surprising since under a relatively large amount of delay (e. g. , $d=O(\sqrt{T})$ for convex losses and $d=O(T^{2/3}/\log T)$ for strongly convex losses), the delayed variant of OFW enjoys the same regret bound as that of the original OFW.

PDF Details

JMLR Journal 2022 Journal Article

Projection-free Distributed Online Learning with Sublinear Communication Complexity

Yuanyu Wan
Guanghui Wang
Wei-Wei Tu
Lijun Zhang

To deal with complicated constraints via locally light computations in distributed online learning, a recent study has presented a projection-free algorithm called distributed online conditional gradient (D-OCG), and achieved an $O(T^{3/4})$ regret bound for convex losses, where $T$ is the number of total rounds. However, it requires $T$ communication rounds, and cannot utilize the strong convexity of losses. In this paper, we propose an improved variant of D-OCG, namely D-BOCG, which can attain the same $O(T^{3/4})$ regret bound with only $O(\sqrt{T})$ communication rounds for convex losses, and a better regret bound of $O(T^{2/3}(\log T)^{1/3})$ with fewer $O(T^{1/3}(\log T)^{2/3})$ communication rounds for strongly convex losses. The key idea is to adopt a delayed update mechanism that reduces the communication complexity, and redefine the surrogate loss function in D-OCG for exploiting the strong convexity. Furthermore, we provide lower bounds to demonstrate that the $O(\sqrt{T})$ communication rounds required by D-BOCG are optimal (in terms of $T$) for achieving the $O(T^{3/4})$ regret with convex losses, and the $O(T^{1/3}(\log T)^{2/3})$ communication rounds required by D-BOCG are near-optimal (in terms of $T$) for achieving the $O(T^{2/3}(\log T)^{1/3})$ regret with strongly convex losses up to polylogarithmic factors. Finally, to handle the more challenging bandit setting, in which only the loss value is available, we incorporate the classical one-point gradient estimator into D-BOCG, and obtain similar theoretical guarantees. [abs] [ pdf ][ bib ] &copy JMLR 2022. ( edit, beta )

PDF Details

AAAI Conference 2021 Conference Paper

Approximate Multiplication of Sparse Matrices with Limited Space

Yuanyu Wan
Lijun Zhang

Approximate matrix multiplication with limited space has received ever-increasing attention due to the emergence of large-scale applications. Recently, based on a popular matrix sketching algorithm—frequent directions, previous work has introduced co-occuring directions (COD) to reduce the approximation error for this problem. Although it enjoys the space complexity of O((mx + my)`) for two input matrices X ∈ Rmx×n and Y ∈ Rmy×n where ` is the sketch size, its time complexity is O (n(mx + my + `)`), which is still very high for large input matrices. In this paper, we propose to reduce the time complexity by exploiting the sparsity of the input matrices. The key idea is to employ an approximate singular value decomposition (SVD) method which can utilize the sparsity, to reduce the number of QR decompositions required by COD. In this way, we develop sparse cooccuring directions, which reduces the time complexity to e O (nnz(X) + nnz(Y ))` + n`2 in expectation while keeps the same space complexity as O((mx + my)`), where nnz(X) denotes the number of non-zero entries in X and the e O notation hides constant factors as well as polylogarithmic factors. Theoretical analysis reveals that the approximation error of our algorithm is almost the same as that of COD. Furthermore, we empirically verify the efficiency and effectiveness of our algorithm.

PDF Details

NeurIPS Conference 2021 Conference Paper

Online Convex Optimization with Continuous Switching Constraint

Guanghui Wang
Yuanyu Wan
Tianbao Yang
Lijun Zhang

In many sequential decision making applications, the change of decision would bring an additional cost, such as the wear-and-tear cost associated with changing server status. To control the switching cost, we introduce the problem of online convex optimization with continuous switching constraint, where the goal is to achieve a small regret given a budget on the \emph{overall} switching cost. We first investigate the hardness of the problem, and provide a lower bound of order $\Omega(\sqrt{T})$ when the switching cost budget $S=\Omega(\sqrt{T})$, and $\Omega(\min\{\frac{T}{S}, T\})$ when $S=O(\sqrt{T})$, where $T$ is the time horizon. The essential idea is to carefully design an adaptive adversary, who can adjust the loss function according to the cumulative switching cost of the player incurred so far based on the orthogonal technique. We then develop a simple gradient-based algorithm which enjoys the minimax optimal regret bound. Finally, we show that, for strongly convex functions, the regret bound can be improved to $O(\log T)$ for $S=\Omega(\log T)$, and $O(\min\{T/\exp(S)+S, T\})$ for $S=O(\log T)$.

PDF Details

AAAI Conference 2021 Conference Paper

Projection-free Online Learning in Dynamic Environments

Yuanyu Wan
Bo Xue
Lijun Zhang

To efficiently solve high-dimensional problems with complicated constraints, projection-free online learning has received ever-increasing research interest. However, previous studies either focused on static regret that is not suitable for dynamic environments, or only established the dynamic regret bound under the smoothness of losses. In this paper, without the condition of the smoothness, we propose a novel projection-free online algorithm, and achieve an O(max{T2/3 V 1/3 T, √ T}) dynamic regret bound for convex functions and an O(max{ √ TVT log T, log T}) dynamic regret bound for strongly convex functions, where T is the time horizon and VT denotes the variation of loss functions. Specifically, we first improve an existing projection-free algorithm called online conditional gradient (OCG) to enjoy small dynamic regret bounds with the prior knowledge of VT. To work with unknowable VT, we maintain multiple instances of the improved OCG that can handle different functional variations, and combine them with a meta-algorithm that can track the best one. Experimental results validate the efficiency and effectiveness of our algorithm.

PDF Details

AAAI Conference 2021 Conference Paper

Projection-free Online Learning over Strongly Convex Sets

Yuanyu Wan
Lijun Zhang

To efficiently solve online problems with complicated constraints, projection-free algorithms including online frankwolfe (OFW) and its variants have received significant interest recently. However, in the general case, existing efficient projection-free algorithms only achieved the regret bound of O(T3/4 ), which is worse than the regret of projection-based algorithms, where T is the number of decision rounds. In this paper, we study the special case of online learning over strongly convex sets, for which we first prove that OFW can enjoy a better regret bound of O(T2/3 ) for general convex losses. The key idea is to refine the decaying step-size in the original OFW by a simple line search rule. Furthermore, for strongly convex losses, we propose a strongly convex variant of OFW by redefining the surrogate loss function in OFW. We show that it achieves a regret bound of O(T2/3 ) over general convex sets and a better regret bound of O( √ T) over strongly convex sets.

PDF Details

ICML Conference 2020 Conference Paper

Projection-free Distributed Online Convex Optimization with $O(\sqrt{T})$ Communication Complexity

Yuanyu Wan
Wei-Wei Tu
Lijun Zhang 0005

Details

IJCAI Conference 2018 Conference Paper

Efficient Adaptive Online Learning via Frequent Directions

Yuanyu Wan
Nan Wei
Lijun Zhang

By employing time-varying proximal functions, adaptive subgradient methods (ADAGRAD) have improved the regret bound and been widely used in online learning and optimization. However, ADAGRAD with full matrix proximal functions (ADA-FULL) cannot deal with large-scale problems due to the impractical time and space complexities, though it has better performance when gradients are correlated. In this paper, we propose ADA-FD, an efficient variant of ADA-FULL based on a deterministic matrix sketching technique called frequent directions. Following ADA-FULL, we incorporate our ADA-FD into both primal-dual subgradient method and composite mirror descent method to develop two efficient methods. By maintaining and manipulating low-rank matrices, at each iteration, the space complexity is reduced from $O(d^2)$ to $O(\tau d)$ and the time complexity is reduced from $O(d^3)$ to $O(\tau^2d)$, where $d$ is the dimensionality of the data and $\tau \ll d$ is the sketching size. Theoretical analysis reveals that the regret of our methods is close to that of ADA-FULL as long as the outer product matrix of gradients is approximately low-rank. Experimental results show that our ADA-FD is comparable to ADA-FULL and outperforms other state-of-the-art algorithms in online convex optimization as well as in training convolutional neural networks (CNN).

PDF Details