Author name cluster

Prashant Khanduri

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.

14 papers

2 author rows

AAAI Conference 2026 Conference Paper

Not All Tokens Are Meant to Be Forgotten

Xiangyu Zhou
Yao Qiang
Saleh Zare Zade
Douglas Zytko
Prashant Khanduri
Dongxiao Zhu

Large Language Models (LLMs), pre-trained on massive text corpora, exhibit remarkable human-level language understanding, reasoning, and decision-making abilities. However, they tend to memorize unwanted information, such as private or copyrighted content, raising significant privacy and legal concerns. Unlearning has emerged as a promising solution, but existing methods face a significant challenge of over-forgetting. This issue arises because they indiscriminately suppress the generation of all the tokens in forget samples, leading to a substantial loss of model utility. To overcome this challenge, we introduce the Targeted Information Forgetting (TIF) framework, which consists of (1) a flexible targeted information identifier designed to differentiate between unwanted words (UW) and general words (GW) in the forget samples, and (2) a novel Targeted Preference Optimization approach that leverages Logit Preference Loss to unlearn unwanted information associated with UW and Preservation Loss to retain general information in GW, effectively improving the unlearning process while mitigating utility degradation. Extensive experiments on the TOFU and MUSE benchmarks demonstrate that the proposed TIF framework enhances unlearning effectiveness while preserving model utility and achieving state-of-the-art results.

PDF Details DOI

ECAI Conference 2025 Conference Paper

Automatic Calibration for Membership Inference Attack on Large Language Models

Saleh Zare Zade
Yao Qiang
Xiangyu Zhou 0001
Hui Zhu 0016
Mohammad Amin Roshani
Prashant Khanduri
Dongxiao Zhu

Membership Inference Attacks (MIAs) have recently been employed to determine whether a specific text was part of the pre-training data of Large Language Models (LLMs). However, existing methods often misinfer non-members as members, leading to a high false positive rate, or depend on additional reference models for probability calibration, which limits their practicality. To overcome these challenges, we introduce a novel framework called Automatic Calibration Membership Inference Attack (ACMIA), which utilizes a tunable temperature to calibrate output probabilities effectively. This approach is inspired by our theoretical insights into maximum likelihood estimation during the pre-training of LLMs. We introduce ACMIA in three configurations designed to accommodate different levels of model access and increase the probability gap between members and non-members, improving the reliability and robustness of membership inference. Extensive experiments on various open-source LLMs demonstrate that our proposed attack is highly effective, robust, and generalizable, surpassing state-of-the-art baselines across three widely used benchmarks. The source code is publicly available.

Details

TMLR Journal 2025 Journal Article

Distributed Hierarchical Decomposition Framework for Multimodal Timeseries Prediction

Wei Ye
Prashant Khanduri
Jiangweizhi Peng
Feng Tian
Jun Gao
Jie Ding
Zhi-Li Zhang
Mingyi Hong

We consider a distributed time series forecasting problem where multiple distributed nodes each observing a local time series (of potentially different modality) collaborate to make both local and global forecasts. This problem is particularly challenging because each node only observes time series generated from a subset of sources, making it challenging to utilize correlations among different streams for accurate forecasting; and the data streams observed at each node may represent different modalities, leading to heterogeneous computational requirements among nodes. To tackle these challenges, we propose a hierarchical learning framework, consisting of multiple local models and a global model, and provide a suite of efficient training algorithms to achieve high local and global forecasting accuracy. We theoretically establish the convergence of the proposed framework and demonstrate the effectiveness of the proposed approach using several time series forecasting tasks, with the (somewhat surprising) observation that the proposed distributed models can match, or even outperform centralized ones.

PDF Details

ECAI Conference 2025 Conference Paper

GeoSAM: Fine-Tuning SAM with Multi-Modal Prompts for Mobility Infrastructure Segmentation

Rafi Ibn Sultan
Chengyin Li
Hui Zhu 0016
Prashant Khanduri
Marco Brocanelli
Dongxiao Zhu

In geographical image segmentation, performance is often constrained by the limited availability of training data and a lack of generalizability, particularly for segmenting mobility infrastructure such as roads, sidewalks, and crosswalks. Vision foundation models like the Segment Anything Model (SAM), pre-trained on millions of natural images, have demonstrated impressive zero-shot segmentation performance, providing a potential solution. However, SAM struggles with geographical images, such as aerial and satellite imagery, due to its training being confined to natural images and the narrow features and textures of these objects blending into their surroundings. To address these challenges, we propose Geographical SAM (GeoSAM), a SAM-based framework that fine-tunes SAM using automatically generated multi-modal prompts. Specifically, GeoSAM integrates point prompts from a pre-trained task-specific model as primary visual guidance, and text prompts generated by a large language model as secondary semantic guidance, enabling the model to better capture both spatial structure and contextual meaning. GeoSAM outperforms existing approaches for mobility infrastructure segmentation in both familiar and completely unseen regions by at least 5% in mIoU, representing a significant leap in leveraging foundation models to segment mobility infrastructure, including both road and pedestrian infrastructure in geographical images. The source code is publicly available.

Details

TMLR Journal 2025 Journal Article

Linear Convergence of Decentralized FedAvg for PL Objectives: The Interpolation Regime

Shruti P Maralappanavar
Prashant Khanduri
Bharath B N

Federated Learning (FL) is a distributed learning paradigm where multiple clients each having access to a local dataset collaborate to solve a joint problem. Federated Averaging (FedAvg) the algorithm of choice has been widely explored in the classical {\em server} setting where the server coordinates the information sharing among clients. However, the performance of FedAvg in the {\em decentralized} setting where only the neighboring clients communicate with each other depending on the network topology is not well understood, especially in the interpolation regime, a common phenomenon observed in modern overparameterized neural networks. In this work, we address this challenge and perform a thorough theoretical performance analysis of FedAvg in the interpolation regime under {\em decentralized} setting. We consider a class of non-convex functions satisfying the Polyak-{\L}ojasiewicz (PL) inequality, a condition satisfied by overparameterized neural networks. For the first time, we establish that {\em Decentralized} FedAvg achieves linear convergence rates of $\mathcal{O}({T^2} \log ({1}/{\epsilon}))$, where $\epsilon$ is the solution accuracy, and $T$ is the number of local updates at each client. We also extend our analysis to the classical {\em Server} FedAvg and establish a convergence rate of $\mathcal{O}(\log ({1}/{\epsilon}))$ which significantly improves upon the best-known rates for the simpler strongly-convex setting. In contrast to the standard FedAvg analyses, our work does not require bounded heterogeneity and gradient assumptions. Instead, we show that sample-wise (and local) smoothness of the local objectives suffice to capture the effect of heterogeneity. Experiments on multiple real datasets corroborate our theoretical findings.

PDF Details

ICML Conference 2024 Conference Paper

Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participation

Haibo Yang 0001
Peiwen Qiu
Prashant Khanduri
Minghong Fang
Jia Liu 0002

Existing works in federated learning (FL) often assume either full client or uniformly distributed client participation. However, in reality, some clients may never participate in FL training (aka incomplete client participation) due to various system heterogeneity factors. A popular solution is the server-assisted federated learning (SA-FL) framework, where the server uses an auxiliary dataset. Despite empirical evidence of SA-FL’s effectiveness in addressing incomplete client participation, theoretical understanding of SA-FL is lacking. Furthermore, the effects of incomplete client participation in conventional FL are poorly understood. This motivates us to rigorously investigate SA-FL. Toward this end, we first show that conventional FL is not PAC-learnable under incomplete client participation in the worst case. Then, we show that the PAC-learnability of FL with incomplete client participation can indeed be revived by SA-FL, which theoretically justifies the use of SA-FL for the first time. Lastly, to provide practical guidance for SA-FL training under incomplete client participation, we propose the SAFARI (server-assisted federated averaging) algorithm that enjoys the same linear convergence speedup guarantees as classic FL with ideal client participation assumptions, offering the first SA-FL algorithm with convergence guarantee. Extensive experiments on different datasets show SAFARI significantly improves the performance under incomplete client participation.

Details

ICML Conference 2023 Conference Paper

FedAvg Converges to Zero Training Loss Linearly for Overparameterized Multi-Layer Neural Networks

Bingqing Song
Prashant Khanduri
Xinwei Zhang 0001
Jinfeng Yi
Mingyi Hong 0001

Federated Learning (FL) is a distributed learning paradigm that allows multiple clients to learn a joint model by utilizing privately held data at each client. Significant research efforts have been devoted to develop advanced algorithms that deal with the situation where the data at individual clients have heterogeneous distributions. In this work, we show that data heterogeneity can be dealt from a different perspective. That is, by utilizing a certain overparameterized multi-layer neural network at each client, even the vanilla FedAvg (a. k. a. the Local SGD) algorithm can accurately optimize the training problem: When each client has a neural network with one wide layer of size $N$ (where $N$ is the number of total training samples), followed by layers of smaller widths, FedAvg converges linearly to a solution that achieves (almost) zero training loss, without requiring any assumptions on the clients’ data distributions. To our knowledge, this is the first work that demonstrates such resilience to data heterogeneity for FedAvg when trained on multi-layer neural networks. Our experiments also confirm that, neural networks of large size can achieve better and more stable performance for FL problems.

Details

ICML Conference 2023 Conference Paper

Linearly Constrained Bilevel Optimization: A Smoothed Implicit Gradient Approach

Prashant Khanduri
Ioannis C. Tsaknakis
Yihua Zhang
Jia Liu 0002
Sijia Liu 0001
Jiawei Zhang 0007
Mingyi Hong 0001

This work develops analysis and algorithms for solving a class of bilevel optimization problems where the lower-level (LL) problems have linear constraints. Most of the existing approaches for constrained bilevel problems rely on value function-based approximate reformulations, which suffer from issues such as non-convex and non-differentiable constraints. In contrast, in this work, we develop an implicit gradient-based approach, which is easy to implement, and is suitable for machine learning applications. We first provide an in-depth understanding of the problem, by showing that the implicit objective for such problems is in general non-differentiable. However, if we add some small (linear) perturbation to the LL objective, the resulting implicit objective becomes differentiable almost surely. This key observation opens the door for developing (deterministic and stochastic) gradient-based algorithms similar to the state-of-the-art ones for unconstrained bi-level problems. We show that when the implicit function is assumed to be strongly-convex, convex, and weakly-convex, the resulting algorithms converge with guaranteed rate. Finally, we experimentally corroborate the theoretical findings and evaluate the performance of the proposed framework on numerical and adversarial learning problems.

Details

ICML Conference 2023 Conference Paper

Prometheus: Taming Sample and Communication Complexities in Constrained Decentralized Stochastic Bilevel Learning

Zhuqing Liu
Xin Zhang 0054
Prashant Khanduri
Songtao Lu
Jia Liu 0002

In recent years, decentralized bilevel optimization has gained significant attention thanks to its versatility in modeling a wide range of multi-agent learning problems, such as multi-agent reinforcement learning and multi-agent meta-learning. However, one unexplored and fundamental problem in this area is how to solve decentralized stochastic bilevel optimization problems with domain constraints while achieving low sample and communication complexities. This problem often arises from multi-agent learning problems with safety constraints. As shown in this paper, constrained decentralized bilevel optimization is far more challenging than its unconstrained counterpart due to the complex coupling structure, which necessitates new algorithm design and analysis techniques. Toward this end, we investigate a class of constrained decentralized bilevel optimization problems, where multiple agents collectively solve a nonconvex-strongly-convex bilevel problem with constraints in the upper-level variables. We propose an algorithm called Prometheus (proximal tracked stochastic recursive estimator) that achieves the first $\mathcal{O}(\epsilon^{-1})$ results in both sample and communication complexities for constrained decentralized bilevel optimization, where $\epsilon>0$ is a desired stationarity error. Collectively, the results in this work contribute to a theoretical foundation for low sample- and communication-complexity constrained decentralized bilevel learning.

Details

ICML Conference 2022 Conference Paper

Anarchic Federated Learning

Haibo Yang 0001
Xin Zhang 0054
Prashant Khanduri
Jia Liu 0002

Present-day federated learning (FL) systems deployed over edge networks consists of a large number of workers with high degrees of heterogeneity in data and/or computing capabilities, which call for flexible worker participation in terms of timing, effort, data heterogeneity, etc. To satisfy the need for flexible worker participation, we consider a new FL paradigm called “Anarchic Federated Learning” (AFL) in this paper. In stark contrast to conventional FL models, each worker in AFL has the freedom to choose i) when to participate in FL, and ii) the number of local steps to perform in each round based on its current situation (e. g. , battery level, communication channels, privacy concerns). However, such chaotic worker behaviors in AFL impose many new open questions in algorithm design. In particular, it remains unclear whether one could develop convergent AFL training algorithms, and if yes, under what conditions and how fast the achievable convergence speed is. Toward this end, we propose two Anarchic Federated Averaging (AFA) algorithms with two-sided learning rates for both cross-device and cross-silo settings, which are named AFA-CD and AFA-CS, respectively. Somewhat surprisingly, we show that, under mild anarchic assumptions, both AFL algorithms achieve the best known convergence rate as the state-of-the-art algorithms for conventional FL. Moreover, they retain the highly desirable linear speedup effect with respect of both the number of workers and local steps in the new AFL paradigm. We validate the proposed algorithms with extensive experiments on real-world datasets.

Details

ICLR Conference 2022 Conference Paper

Decentralized Learning for Overparameterized Problems: A Multi-Agent Kernel Approximation Approach

Prashant Khanduri
Haibo Yang 0001
Mingyi Hong 0001
Jia Liu 0002
Hoi-To Wai
Sijia Liu 0001

This work develops a novel framework for communication-efficient distributed learning where the models to be learned are overparameterized. We focus on a class of kernel learning problems (which includes the popular neural tangent kernel (NTK) learning as a special case) and propose a novel {\it multi-agent kernel approximation} technique that allows the agents to distributedly estimate the full kernel function, and subsequently perform decentralized optimization, without directly exchanging any local data or parameters. The proposed framework is a significant departure from the classical consensus-based approaches, because the agents do not exchange problem parameters, and no consensus is required. We analyze the optimization and the generalization performance of the proposed framework for the $\ell_2$ loss. We show that with $M$ agents and $N$ total samples when certain generalized inner-product kernels (resp. the random features kernel) are used, each agent needs to communicate $\mathcal{O}\big({N^2}/{M}\big)$ bits (resp. $\mathcal{O}\big(N \sqrt{N}/M \big)$ real values) to achieve minimax optimal generalization performance. We validate the theoretical results on 90 UCI benchmarking datasets (with average data size $N \approx 1000$) and show that each agent needs to share a total of $200N/M$ bits (resp. $3N/M$ real values) to closely match the performance of the centralized algorithms, and these numbers are independent of parameter and feature dimensions.

Details

ICML Conference 2022 Conference Paper

Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization

Yihua Zhang
Guanhua Zhang
Prashant Khanduri
Mingyi Hong 0001
Shiyu Chang
Sijia Liu 0001

Adversarial training (AT) is a widely recognized defense mechanism to gain the robustness of deep neural networks against adversarial attacks. It is built on min-max optimization (MMO), where the minimizer (i. e. , defender) seeks a robust model to minimize the worst-case training loss in the presence of adversarial examples crafted by the maximizer (i. e. , attacker). However, the conventional MMO method makes AT hard to scale. Thus, Fast-AT and other recent algorithms attempt to simplify MMO by replacing its maximization step with the single gradient sign-based attack generation step. Although easy to implement, FAST-AT lacks theoretical guarantees, and its empirical performance is unsatisfactory due to the issue of robust catastrophic overfitting when training with strong adversaries. In this paper, we advance Fast-AT from the fresh perspective of bi-level optimization (BLO). We first show that the commonly-used Fast-AT is equivalent to using a stochastic gradient algorithm to solve a linearized BLO problem involving a sign operation. However, the discrete nature of the sign operation makes it difficult to understand the algorithm performance. Inspired by BLO, we design and analyze a new set of robust training algorithms termed Fast Bi-level AT (Fast-BAT), which effectively defends sign-based projected gradient descent (PGD) attacks without using any gradient sign method or explicit robust regularization. In practice, we show that our method yields substantial robustness improvements over multiple baselines across multiple models and datasets.

Details

NeurIPS Conference 2021 Conference Paper

A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum

Prashant Khanduri
Siliang Zeng
Mingyi Hong
Hoi-To Wai
Zhaoran Wang
Zhuoran Yang

This paper proposes a new algorithm -- the \underline{S}ingle-timescale Do\underline{u}ble-momentum \underline{St}ochastic \underline{A}pprox\underline{i}matio\underline{n} (SUSTAIN) -- for tackling stochastic unconstrained bilevel optimization problems. We focus on bilevel problems where the lower level subproblem is strongly-convex and the upper level objective function is smooth. Unlike prior works which rely on \emph{two-timescale} or \emph{double loop} techniques, we design a stochastic momentum-assisted gradient estimator for both the upper and lower level updates. The latter allows us to control the error in the stochastic gradient updates due to inaccurate solution to both subproblems. If the upper objective function is smooth but possibly non-convex, we show that {SUSTAIN}~requires $O(\epsilon^{-3/2})$ iterations (each using $O(1)$ samples) to find an $\epsilon$-stationary solution. The $\epsilon$-stationary solution is defined as the point whose squared norm of the gradient of the outer function is less than or equal to $\epsilon$. The total number of stochastic gradient samples required for the upper and lower level objective functions matches the best-known complexity for single-level stochastic gradient algorithms. We also analyze the case when the upper level objective function is strongly-convex.

PDF Details

NeurIPS Conference 2021 Conference Paper

STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning

Prashant Khanduri
Pranay Sharma
Haibo Yang
Mingyi Hong
Jia Liu
Ketan Rajawat
Pramod Varshney

Federated Learning (FL) refers to the paradigm where multiple worker nodes (WNs) build a joint model by using local data. Despite extensive research, for a generic non-convex FL problem, it is not clear, how to choose the WNs' and the server's update directions, the minibatch sizes, and the local update frequency, so that the WNs use the minimum number of samples and communication rounds to achieve the desired solution. This work addresses the above question and considers a class of stochastic algorithms where the WNs perform a few local updates before communication. We show that when both the WN's and the server's directions are chosen based on certain stochastic momentum estimator, the algorithm requires $\tilde{\mathcal{O}}(\epsilon^{-3/2})$ samples and $\tilde{\mathcal{O}}(\epsilon^{-1})$ communication rounds to compute an $\epsilon$-stationary solution. To the best of our knowledge, this is the first FL algorithm that achieves such {\it near-optimal} sample and communication complexities simultaneously. Further, we show that there is a trade-off curve between local update frequencies and local minibatch sizes, on which the above sample and communication complexities can be maintained. {Finally, we show that for the classical FedAvg (a. k. a. Local SGD, which is a momentum-less special case of the STEM), a similar trade-off curve exists, albeit with worse sample and communication complexities. Our insights on this trade-off provides guidelines for choosing the four important design elements for FL algorithms, the update frequency, directions, and minibatch sizes to achieve the best performance. }

PDF Details