Author name cluster

Bin Gu 0001

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.

24 papers

1 author row

ICLR Conference 2025 Conference Paper

Collaborative Discrete-Continuous Black-Box Prompt Learning for Language Models

Hualin Zhang
Haozhen Zhang
Zhekai Liu
Bin Gu 0001
Yi Chang 0001

Large Scale Pre-Trained Language Models (PTMs) have demonstrated unprecedented capabilities across diverse natural language processing tasks. Adapting such models to downstream tasks is computationally intensive and time-consuming, particularly in black-box scenarios common in Language-Model-as-a-Service (LMaaS) environments, where model parameters and gradients are inaccessible. Recently, black-box prompt learning using zeroth-order gradients has emerged as a promising approach to address these challenges by optimizing learnable continuous prompts in embedding spaces, starting with \textit{randomly initialized discrete text prompts}. However, its reliance on randomly initialized discrete prompts limits adaptability to diverse downstream tasks or models. To address this limitation, this paper introduces ZO-PoG, a novel framework that optimizes prompts through a collaborative approach, combining Policy Gradient optimization for initial discrete text prompts and Zeroth-Order optimization for continuous prompts in embedding space. By optimizing collaboratively between discrete and continuous prompts, ZO-PoG maximizes adaptability to downstream tasks, achieving superior results without direct access to the model’s internal structures. Importantly, we establish the sub-linear convergence of ZO-PoG under mild assumptions. The experiments on different datasets demonstrate significant improvements in various tasks compared to the baselines.

ICLR Conference 2025 Conference Paper

Event-Driven Online Vertical Federated Learning

Ganyu Wang
Boyu Wang 0004
Bin Gu 0001
Charles X. Ling

Online learning is more adaptable to real-world scenarios in Vertical Federated Learning (VFL) compared to offline learning. However, integrating online learning into VFL presents challenges due to the unique nature of VFL, where clients possess non-intersecting feature sets for the same sample. In real-world scenarios, the clients may not receive data streaming for the disjoint features for the same entity synchronously. Instead, the data are typically generated by an *event* relevant to only a subset of clients. We are the first to identify these challenges in online VFL, which have been overlooked by previous research. To address these challenges, we proposed an event-driven online VFL framework. In this framework, only a subset of clients were activated during each event, while the remaining clients passively collaborated in the learning process. Furthermore, we incorporated *dynamic local regret (DLR)* into VFL to address the challenges posed by online learning problems with non-convex models within a non-stationary environment. We conducted a comprehensive regret analysis of our proposed framework, specifically examining the DLR under non-convex conditions with event-driven online VFL. Extensive experiments demonstrated that our proposed framework was more stable than the existing online VFL framework under non-stationary data conditions while also significantly reducing communication and computation costs.

ICML Conference 2025 Conference Paper

FedOne: Query-Efficient Federated Learning for Black-box Discrete Prompt Learning

Ganyu Wang
Jinjie Fang
Maxwell J. Yin
Bin Gu 0001
Xi Chen 0009
Boyu Wang 0004
Yi Chang 0001
Charles X. Ling

Black-Box Discrete Prompt Learning (BDPL) is a prompt-tuning method that optimizes discrete prompts without accessing model parameters or gradients, making the prompt tuning on a cloud-based Large Language Model (LLM) feasible. Adapting Federated Learning (FL) to BDPL could further enhance prompt tuning performance by leveraging data from diverse sources. However, all previous research on federated black-box prompt tuning had neglected the substantial query cost associated with the cloud-based LLM service. To address this gap, we conducted a theoretical analysis of query efficiency within the context of federated black-box prompt tuning. Our findings revealed that degrading FedAvg to activate only one client per round, a strategy we called FedOne, enabled optimal query efficiency in federated black-box prompt learning. Building on this insight, we proposed the FedOne framework, a federated black-box discrete prompt learning method designed to maximize query efficiency when interacting with cloud-based LLMs. We conducted numerical experiments on various aspects of our framework, demonstrating a significant improvement in query efficiency, which aligns with our theoretical results.

ICLR Conference 2025 Conference Paper

Improving Generalization and Robustness in SNNs Through Signed Rate Encoding and Sparse Encoding Attacks

Bhaskar Mukhoty
Hilal AlQuabeh
Bin Gu 0001

Rate-encoded spiking neural networks (SNNs) are known to offer superior adversarial robustness compared to direct-encoded SNNs but have relatively poor generalization on clean input. While the latter offers good generalization on clean input it suffers poor adversarial robustness under standard training. A key reason for this difference is the input noise introduced by the rate encoding, which encodes a pixel intensity with $T$ independent Bernoulli samples. To improve the generalization of rate-encoded SNNs, we propose the *signed rate encoding* (sRATE) that allows mean centering of the input and helps reduce the randomness introduced by the encoding, resulting in improved clean accuracy. In contrast to rate encoding, where input restricted to $[0,1]^d$ is encoded in $\\{0,1\\}^{d\times T}$, the signed rate encoding allows input in $[-1,1]^d$ to be encoded with spikes in $\\{-1,0,1\\}^{d\times T}$, where positive (negative) inputs are encoded with positive (negative) spikes. We further construct efficient \textit{Sparse Encoding Attack} (SEA) on standard and signed rate encoded input, which performs $l_0$-norm restricted adversarial attack in the discrete encoding space. We prove the theoretical optimality of the attack under the first-order approximation of the loss and compare it empirically with the existing attacks on the input space. Adversarial training performed with SEA, under signed rate encoding, offers superior adversarial robustness to the existing attacks and itself. Experiments conducted on standard datasets show the effectiveness of sign rate encoding in improving accuracy across all settings including adversarial robustness. The code is available at https://github.com/BhaskarMukhoty/SignedRateEncoding

ICML Conference 2025 Conference Paper

Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees

William de Vazelhes
Xiao-Tong Yuan
Bin Gu 0001

In sparse optimization, enforcing hard constraints using the $\ell_0$ pseudo-norm offers advantages like controlled sparsity compared to convex relaxations. However, many real-world applications demand not only sparsity constraints but also some extra constraints. While prior algorithms have been developed to address this complex scenario with mixed combinatorial and convex constraints, they typically require the closed form projection onto the mixed constraints which might not exist, and/or only provide local guarantees of convergence which is different from the global guarantees commonly sought in sparse optimization. To fill this gap, in this paper, we study the problem of sparse optimization with extra support-preserving constraints commonly encountered in the literature. We present a new variant of iterative hard-thresholding algorithm equipped with a two-step consecutive projection operator customized for these mixed constraints, serving as a simple alternative to the Euclidean projection onto the mixed constraint. By introducing a novel trade-off between sparsity relaxation and sub-optimality, we provide global guarantees in objective value for the output of our algorithm, in the deterministic, stochastic, and zeroth-order settings, under the conventional restricted strong-convexity/smoothness assumptions. As a fundamental contribution in proof techniques, we develop a novel extension of the classic three-point lemma to the considered two-step non-convex projection operator, which allows us to analyze the convergence in objective value in an elegant way that has not been possible with existing techniques. In the zeroth-order case, such technique also improves upon the state-of-the-art result from de Vazelhes et. al. (2022), even in the case without additional constraints, by allowing us to remove a non-vanishing system error present in their work.

ICML Conference 2025 Conference Paper

Temporal Misalignment in ANN-SNN Conversion and its Mitigation via Probabilistic Spiking Neurons

Velibor Bojkovic
Xiaofeng Wu 0002
Bin Gu 0001

Spiking Neural Networks (SNNs) offer a more energy-efficient alternative to Artificial Neural Networks (ANNs) by mimicking biological neural principles, establishing them as a promising approach to mitigate the increasing energy demands of large-scale neural models. However, fully harnessing the capabilities of SNNs remains challenging due to their discrete signal processing and temporal dynamics. ANN-SNN conversion has emerged as a practical approach, enabling SNNs to achieve competitive performance on complex machine learning tasks. In this work, we identify a phenomenon in the ANN-SNN conversion framework, termed temporal misalignment, in which random spike rearrangement across SNN layers leads to performance improvements. Based on this observation, we introduce biologically plausible two-phase probabilistic (TPP) spiking neurons, further enhancing the conversion process. We demonstrate the advantages of our proposed method both theoretically and empirically through comprehensive experiments on CIFAR-10/100, CIFAR10-DVS, and ImageNet across a variety of architectures, achieving state-of-the-art results.

ICLR Conference 2024 Conference Paper

Certified Adversarial Robustness for Rate Encoded Spiking Neural Networks

Bhaskar Mukhoty
Hilal AlQuabeh
Giulia De Masi
Huan Xiong
Bin Gu 0001

The spiking neural networks are inspired by the biological neurons that employ binary spikes to propagate information in the neural network. It has garnered considerable attention as the next-generation neural network, as the spiking activity simplifies the computation burden of the network to a large extent and is known for its low energy deployment enabled by specialized neuromorphic hardware. One popular technique to feed a static image to such a network is rate encoding, where each pixel is encoded into random binary spikes, following a Bernoulli distribution that uses the pixel intensity as bias. By establishing a novel connection between rate-encoding and randomized smoothing, we give the first provable robustness guarantee for spiking neural networks against adversarial perturbation of inputs bounded under $l_1$-norm. We introduce novel adversarial training algorithms for rate-encoded models that significantly improve the state-of-the-art empirical robust accuracy result. Experimental validation of the method is performed across various static image datasets, including CIFAR-10, CIFAR-100 and ImageNet-100. The code is available at \url{https://github.com/BhaskarMukhoty/CertifiedSNN}.

ICML Conference 2024 Conference Paper

Double Momentum Method for Lower-Level Constrained Bilevel Optimization

Wanli Shi
Yi Chang 0001
Bin Gu 0001

Bilevel optimization (BO) has recently gained prominence in many machine learning applications due to its ability to capture the nested structure inherent in these problems. Recently, many hypergradient methods have been proposed as effective solutions for solving large-scale problems. However, current hypergradient methods for the lower-level constrained bilevel optimization (LCBO) problems need very restrictive assumptions, namely, where optimality conditions satisfy the differentiability and invertibility conditions, and lack a solid analysis of the convergence rate. What’s worse, existing methods require either double-loop updates, which are sometimes less efficient. To solve this problem, in this paper, we propose a new hypergradient of LCBO leveraging the theory of nonsmooth implicit function theorem instead of using the restrive assumptions. In addition, we propose a single-loop single-timescale algorithm based on the double-momentum method and adaptive step size method and prove it can return a $(\delta, \epsilon)$-stationary point with $\tilde{\mathcal{O}}(d_2^2\epsilon^{-4})$ iterations. Experiments on two applications demonstrate the effectiveness of our proposed method.

ICLR Conference 2024 Conference Paper

DREAM: Dual Structured Exploration with Mixup for Open-set Graph Domain Adaption

Nan Yin
Mengzhu Wang
Zhenghan Chen
Li Shen 0008
Huan Xiong
Bin Gu 0001
Xiao Luo 0001

Recently, numerous graph neural network methods have been developed to tackle domain shifts in graph data. However, these methods presuppose that unlabeled target graphs belong to categories previously seen in the source domain. This assumption could not hold true for in-the-wild target graphs. In this paper, we delve deeper to explore a more realistic problem open-set graph domain adaptation. Our objective is to not only identify target graphs from new categories but also accurately classify remaining target graphs into their respective categories under domain shift and label scarcity. To solve this challenging problem, we introduce a new method named Dual Structured Exploration with Mixup (DREAM). DREAM incorporates a graph-level representation learning branch as well as a subgraph-enhanced branch, which jointly explores graph topological structures from both global and local viewpoints. To maximize the use of unlabeled target graphs, we train these two branches simultaneously using posterior regularization to enhance their inter-module consistency. To accommodate the open-set setting, we amalgamate dissimilar samples to generate virtual unknown samples belonging to novel classes. Moreover, to alleviate domain shift, we establish a k nearest neighbor-based graph-of-graphs and blend multiple neighbors of each sample to produce cross-domain virtual samples for inter-domain consistency learning. Extensive experiments validate the effectiveness of the proposed DREAM in comparison to various state-of-the-art approaches in different settings.

ICLR Conference 2024 Conference Paper

Federated Causal Discovery from Heterogeneous Data

Loka Li
Ignavier Ng
Gongxu Luo
Biwei Huang
Guangyi Chen 0002
Tongliang Liu
Bin Gu 0001
Kun Zhang 0001

Conventional causal discovery methods rely on centralized data, which is inconsistent with the decentralized nature of data in many real-world situations. This discrepancy has motivated the development of federated causal discovery (FCD) approaches. However, existing FCD methods may be limited by their potentially restrictive assumptions of identifiable functional causal models or homogeneous data distributions, narrowing their applicability in diverse scenarios. In this paper, we propose a novel FCD method attempting to accommodate arbitrary causal models and heterogeneous data. We first utilize a surrogate variable corresponding to the client index to account for the data heterogeneity across different clients. We then develop a federated conditional independence test (FCIT) for causal skeleton discovery and establish a federated independent change principle (FICP) to determine causal directions. These approaches involve constructing summary statistics as a proxy of the raw data to protect data privacy. Owing to the nonparametric properties, FCIT and FICP make no assumption about particular functional forms, thereby facilitating the handling of arbitrary causal models. We conduct extensive experiments on synthetic and real datasets to show the efficacy of our method. The code is available at https://github.com/lokali/FedCDH.git.

ICLR Conference 2024 Conference Paper

General Stability Analysis for Zeroth-Order Optimization Algorithms

Xinyue Liu
Hualin Zhang
Bin Gu 0001
Hong Chen 0004

Zeroth-order optimization algorithms are widely used for black-box optimization problems, such as those in machine learning and prompt engineering, where the gradients are approximated using function evaluations. Recently, a generalization result was provided for zeroth-order stochastic gradient descent (SGD) algorithms through stability analysis. However, this result was limited to the vanilla 2-point zeroth-order estimate of Gaussian distribution used in SGD algorithms. To address these limitations, we propose a general proof framework for stability analysis that applies to convex, strongly convex, and non-convex conditions, and yields results for popular zeroth-order optimization algorithms, including SGD, GD, and SVRG, as well as various zeroth-order estimates, such as 1-point and 2-point with different distributions and coordinate estimates. Our general analysis shows that coordinate estimation can lead to tighter generalization bounds for SGD, GD, and SVRG versions of zeroth-order optimization algorithms, due to the smaller expansion brought by coordinate estimates to stability analysis.

ICLR Conference 2024 Conference Paper

Learning No-Regret Sparse Generalized Linear Models with Varying Observation(s)

Diyang Li
Charles X. Ling
Zhiqiang Xu
Huan Xiong
Bin Gu 0001

Generalized Linear Models (GLMs) encompass a wide array of regression and classification models, where prediction is a function of a linear combination of the input variables. Often in real-world scenarios, a number of observations would be added into or removed from the existing training dataset, necessitating the development of learning systems that can efficiently train optimal models with varying observations in an online (sequential) manner instead of retraining from scratch. Despite the significance of data-varying scenarios, most existing approaches to sparse GLMs concentrate on offline batch updates, leaving online solutions largely underexplored. In this work, we present the first algorithm without compromising accuracy for GLMs regularized by sparsity-enforcing penalties trained on varying observations. Our methodology is capable of handling the addition and deletion of observations simultaneously, while adaptively updating data-dependent regularization parameters to ensure the best statistical performance. Specifically, we recast sparse GLMs as a bilevel optimization objective upon varying observations and characterize it as an explicit gradient flow in the underlying space for the inner and outer subproblems we are optimizing over, respectively. We further derive a set of rules to ensure a proper transition at regions of non-smoothness, and establish the guarantees of theoretical consistency and finite convergence. Encouraging results are exhibited on real-world benchmarks.

ICML Conference 2024 Conference Paper

NDOT: Neuronal Dynamics-based Online Training for Spiking Neural Networks

Haiyan Jiang
Giulia De Masi
Huan Xiong
Bin Gu 0001

Spiking Neural Networks (SNNs) are attracting great attention for their energy-efficient and fast-inference properties in neuromorphic computing. However, the efficient training of deep SNNs poses challenges in gradient calculation due to the non-differentiability of their binary spike-generating activation functions. The widely used surrogate gradient (SG) method, combined with the back-propagation through time (BPTT), has shown considerable effectiveness. Yet, BPTT’s process of unfolding and back-propagating along the computation graph requires storing intermediate information at all time-steps, resulting in huge memory consumption and failing to meet online requirements. In this work, we propose Neuronal Dynamics-based Online Training (NDOT) for SNNs, which uses the neuronal dynamics-based temporal dependency/sensitivity in gradient computation. NDOT enables forward-in-time learning by decomposing the full gradient into temporal and spatial gradients. To illustrate the intuition behind NDOT, we employ the Follow-the-Regularized-Leader (FTRL) algorithm. FTRL explicitly utilizes historical information and addresses limitations in instantaneous loss. Our proposed NDOT method accurately captures temporal dependencies through neuronal dynamics, functioning similarly to FTRL’s explicit utilizing historical information. Experiments on CIFAR-10, CIFAR-100, and CIFAR10-DVS demonstrate the superior performance of our NDOT method on large-scale static and neuromorphic datasets within a small number of time steps. The codes are available at https: //github. com/HaiyanJiang/SNN-NDOT.

ICLR Conference 2024 Conference Paper

New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions

Xinzhe Yuan 0001
William de Vazelhes
Bin Gu 0001
Huan Xiong

Hard-thresholding is an important type of algorithm in machine learning that is used to solve $\ell_0$ constrained optimization problems. However, the true gradient of the objective function can be difficult to access in certain scenarios, which normally can be approximated by zeroth-order (ZO) methods. SZOHT algorithm is the only algorithm tackling $\ell_0$ sparsity constraints with zeroth-order gradients so far. Unfortunately, SZOHT has a notable limitation on the number of random directions due to the inherent conflict between the deviation of ZO gradients and the expansivity of the hard-thresholding operator. This paper approaches this problem by considering the role of variance and provides a new insight into variance reduction: mitigating the unique conflicts between ZO gradients and hard-thresholding. Under this perspective, we propose a generalized variance reduced ZO hard-thresholding algorithm as well as the generalized convergence analysis under standard assumptions. The theoretical results demonstrate the new algorithm eliminates the restrictions on the number of random directions, leading to improved convergence rates and broader applicability compared with SZOHT. Finally, we illustrate the utility of our method on a portfolio optimization problem as well as black-box adversarial attacks.

ICLR Conference 2024 Conference Paper

TAB: Temporal Accumulated Batch Normalization in Spiking Neural Networks

Haiyan Jiang
Vincent Zoonekynd
Giulia De Masi
Bin Gu 0001
Huan Xiong

Spiking Neural Networks (SNNs) are attracting growing interest for their energy-efficient computing when implemented on neuromorphic hardware. However, directly training SNNs, even adopting batch normalization (BN), is highly challenging due to their non-differentiable activation function and the temporally delayed accumulation of outputs over time. For SNN training, this temporal accumulation gives rise to Temporal Covariate Shifts (TCS) along the temporal dimension, a phenomenon that would become increasingly pronounced with layer-wise computations across multiple layers and multiple time-steps. In this paper, we introduce TAB (Temporal Accumulated Batch Normalization), a novel SNN batch normalization method that addresses the temporal covariate shift issue by aligning with neuron dynamics (specifically the accumulated membrane potential) and utilizing temporal accumulated statistics for data normalization. Within its framework, TAB effectively encapsulates the historical temporal dependencies that underlie the membrane potential accumulation process, thereby establishing a natural connection between neuron dynamics and TAB batch normalization. Experimental results on CIFAR-10, CIFAR-100, and DVS-CIFAR10 show that our TAB method outperforms other state-of-the-art methods.

ICML Conference 2023 Conference Paper

A Unified Optimization Framework of ANN-SNN Conversion: Towards Optimal Mapping from Activation Values to Firing Rates

Haiyan Jiang
Srinivas Anumasa
Giulia De Masi
Huan Xiong
Bin Gu 0001

Spiking Neural Networks (SNNs) have gained significant attention for their energy-efficient and fast-inference capabilities, but training SNNs from scratch can be challenging due to the discrete nature of spikes. One alternative method is to convert an Artificial Neural Network (ANN) into an SNN, known as ANN-SNN conversion. Currently, existing ANN-SNN conversion methods often involve redesigning the ANN with a new activation function, rather than utilizing the traditional ReLU, and converting it to an SNN. However, these methods do not take into account the potential performance loss between the regular ANN with ReLU and the tailored ANN. In this work, we propose a unified optimization framework for ANN-SNN conversion that considers both performance loss and conversion error. To achieve this, we introduce the SlipReLU activation function, which is a weighted sum of the threshold-ReLU and the step function. Theoretical analysis demonstrates that conversion error can be zero on a range of shift values $\delta \in [-0. 5, 0. 5]$ rather than a fixed shift term 0. 5. We evaluate our SlipReLU method on CIFAR datasets, which shows that SlipReLU outperforms current ANN-SNN conversion methods and supervised training methods in terms of accuracy and latency. To the best of our knowledge, this is the first ANN-SNN conversion method that enables SNN inference using only 1 time step. Code is available at https: //github. com/HaiyanJiang/SNN_Conversion_unified.

ICLR Conference 2023 Conference Paper

Faster Gradient-Free Methods for Escaping Saddle Points

Hualin Zhang
Bin Gu 0001

Escaping from saddle points has become an important research topic in non-convex optimization. In this paper, we study the case when calculations of explicit gradients are expensive or even infeasible, and only function values are accessible. Currently, there have two types of gradient-free (zeroth-order) methods based on random perturbation and negative curvature finding proposed to escape saddle points efficiently and converge to an $\epsilon$-approximate second-order stationary point. Nesterov's accelerated gradient descent (AGD) method can escape saddle points faster than gradient descent (GD) which have been verified in first-order algorithms. However, whether AGD could accelerate the gradient-free methods is still unstudied. To unfold this mystery, in this paper, we propose two accelerated variants for the two types of gradient-free methods of escaping saddle points. We show that our algorithms can find an $\epsilon$-approximate second-order stationary point with $\tilde{\mathcal{O}}(1/\epsilon^{1.75})$ iteration complexity and $\tilde{\mathcal{O}}(d/\epsilon^{1.75})$ oracle complexity, where $d$ is the problem dimension. Thus, our methods achieve a comparable convergence rate to their first-order counterparts and have fewer oracle complexity compared to prior derivative-free methods for finding second-order stationary points.

ICML Conference 2022 Conference Paper

Gradient-Free Method for Heavily Constrained Nonconvex Optimization

Wanli Shi
Hongchang Gao
Bin Gu 0001

Zeroth-order (ZO) method has been shown to be a powerful method for solving the optimization problem where explicit expression of the gradients is difficult or infeasible to obtain. Recently, due to the practical value of the constrained problems, a lot of ZO Frank-Wolfe or projected ZO methods have been proposed. However, in many applications, we may have a very large number of nonconvex white/black-box constraints, which makes the existing zeroth-order methods extremely inefficient (or even not working) since they need to inquire function value of all the constraints and project the solution to the complicated feasible set. In this paper, to solve the nonconvex problem with a large number of white/black-box constraints, we proposed a doubly stochastic zeroth-order gradient method (DSZOG) with momentum method and adaptive step size. Theoretically, we prove DSZOG can converge to the $\epsilon$-stationary point of the constrained problem. Experimental results in two applications demonstrate the superiority of our method in terms of training time and accuracy compared with other ZO methods for the constrained problem.

ICML Conference 2022 Conference Paper

The power of first-order smooth optimization for black-box non-smooth problems

Alexander V. Gasnikov
Anton Novitskii
Vasilii Novitskii
Farshed Abdukhakimov
Dmitry Kamzolov
Aleksandr Beznosikov
Martin Takác 0001
Pavel E. Dvurechensky

Gradient-free/zeroth-order methods for black-box convex optimization have been extensively studied in the last decade with the main focus on oracle calls complexity. In this paper, besides the oracle complexity, we focus also on iteration complexity, and propose a generic approach that, based on optimal first-order methods, allows to obtain in a black-box fashion new zeroth-order algorithms for non-smooth convex optimization problems. Our approach not only leads to optimal oracle complexity, but also allows to obtain iteration complexity similar to first-order methods, which, in turn, allows to exploit parallel computations to accelerate the convergence of our algorithms. We also elaborate on extensions for stochastic optimization problems, saddle-point problems, and distributed optimization.

ICML Conference 2020 Conference Paper

Fast OSCAR and OWL Regression via Safe Screening Rules

Runxue Bao
Bin Gu 0001
Heng Huang 0001

Ordered Weighted $L_{1}$ (OWL) regularized regression is a new regression analysis for high-dimensional sparse learning. Proximal gradient methods are used as standard approaches to solve OWL regression. However, it is still a burning issue to solve OWL regression due to considerable computational cost and memory usage when the feature or sample size is large. In this paper, we propose the first safe screening rule for OWL regression by exploring the order of the primal solution with the unknown order structure via an iterative strategy, which overcomes the difficulties of tackling the non-separable regularizer. It effectively avoids the updates of the parameters whose coefficients must be zero during the learning process. More importantly, the proposed screening rule can be easily applied to standard and stochastic proximal gradient methods. Moreover, we prove that the algorithms with our screening rule are guaranteed to have identical results with the original algorithms. Experimental results on a variety of datasets show that our screening rule leads to a significant computational gain without any loss of accuracy, compared to existing competitive algorithms.

ICML Conference 2018 Conference Paper

Decoupled Parallel Backpropagation with Convergence Guarantee

Zhouyuan Huo
Bin Gu 0001
Qian Yang 0003
Heng Huang 0001

Backpropagation algorithm is indispensable for the training of feedforward neural networks. It requires propagating error gradients sequentially from the output layer all the way back to the input layer. The backward locking in backpropagation algorithm constrains us from updating network layers in parallel and fully leveraging the computing resources. Recently, several algorithms have been proposed for breaking the backward locking. However, their performances degrade seriously when networks are deep. In this paper, we propose decoupled parallel backpropagation algorithm for deep learning optimization with convergence guarantee. Firstly, we decouple the backpropagation algorithm using delayed gradients, and show that the backward locking is removed when we split the networks into multiple modules. Then, we utilize decoupled parallel backpropagation in two stochastic methods and prove that our method guarantees convergence to critical points for the non-convex problem. Finally, we perform experiments for training deep convolutional neural networks on benchmark datasets. The experimental results not only confirm our theoretical analysis, but also demonstrate that the proposed method can achieve significant speedup without loss of accuracy.

ICML Conference 2018 Conference Paper

Faster Derivative-Free Stochastic Algorithm for Shared Memory Machines

Bin Gu 0001
Zhouyuan Huo
Cheng Deng 0002
Heng Huang 0001

Asynchronous parallel stochastic gradient optimization has been playing a pivotal role to solve large-scale machine learning problems in big data applications. Zeroth-order (derivative-free) methods estimate the gradient only by two function evaluations, thus have been applied to solve the problems where the explicit gradient calculations are computationally expensive or infeasible. Recently, the first asynchronous parallel stochastic zeroth-order algorithm (AsySZO) was proposed. However, its convergence rate is O(1/SQRT{T}) for the smooth, possibly non-convex learning problems, which is significantly slower than O(1/T) the best convergence rate of (asynchronous) stochastic gradient algorithm. To fill this gap, in this paper, we first point out the fundamental reason leading to the slow convergence rate of AsySZO, and then propose a new asynchronous stochastic zerothorder algorithm (AsySZO+). We provide a faster convergence rate O(1/bT) (b is the mini-batch size) for AsySZO+ by the rigorous theoretical analysis, which is a significant improvement over O(1/SQRT{T}). The experimental results on the application of ensemble learning confirm that our AsySZO+ has a faster convergence rate than the existing (asynchronous) stochastic zeroth-order algorithms.

UAI Conference 2017 Conference Paper

Triply Stochastic Gradients on Multiple Kernel Learning

Xiang Li 0012
Bin Gu 0001
Shuang Ao
Huaimin Wang 0001
Charles X. Ling

Multiple Kernel Learning (MKL) is highly useful for learning complex data with multiple cues or representations. However, MKL is known to have poor scalability because of the expensive kernel computation. Dai et al (2014) proposed to use a doubly Stochastic Gradient Descent algorithm (doubly SGD) to greatly improve the scalability of kernel methods. However, the algorithm is not suitable for MKL because it cannot learn the kernel weights. In this paper, we provide a novel extension to doubly SGD for MKL so that both the decision functions and the kernel weights can be learned simultaneously. To achieve this, we develop the triply Stochastic Gradient Descent (triply SGD) algorithm which involves three sources of randomness – the data points, the random features, and the kernels, which was not considered in previous work. We prove that our algorithm enjoys similar convergence rate as that of doubly SGD. Comparing to several traditional MKL solutions, we show that our method has faster convergence speed and achieved better accuracy. Most importantly, our method makes it possible to learn MKL problems with millions of data points on a normal desktop PC.

ICML Conference 2015 Conference Paper

A New Generalized Error Path Algorithm for Model Selection

Bin Gu 0001
Charles X. Ling

Model selection with cross validation (CV) is very popular in machine learning. However, CV with grid and other common search strategies cannot guarantee to find the model with minimum CV error, which is often the ultimate goal of model selection. Recently, various solution path algorithms have been proposed for several important learning algorithms including support vector classification, Lasso, and so on. However, they still do not guarantee to find the model with minimum CV error. In this paper, we first show that the solution paths produced by various algorithms have the property of piecewise linearity. Then, we prove that a large class of error (or loss) functions are piecewise constant, linear, or quadratic w. r. t. the regularization parameter, based on the solution path. Finally, we propose a new generalized error path algorithm (GEP), and prove that it will find the model with minimum CV error for the entire range of the regularization parameter. The experimental results on a variety of datasets not only confirm our theoretical findings, but also show that the best model with our GEP has better generalization error on the test data, compared to the grid search, manual search, and random search.