10 citations · 21 across the 40 of their papers we have counts for
48 papers
Minimax-Optimal Predictive Flow Matching under Distribution Drift
Aadithya Srikanth, Vaneet Aggarwal
Flow matching learns a generative velocity field by regression, but under distribution drift a field must be deployed before the current data arrive. We study this predictive probl…
Reliable Replay through Spatial Coherence in Online Continual Learning
Haixiang Sun, Jiefu Zhang, Yinghao He +4
Continually adapting models to new tasks requires retaining earlier knowledge under limited memory and computation. Experience replay addresses this challenge, but priorities based…
CARVE: Breaking Data Barriers in Chip Placement by Harnessing Reusable Expertise
Jiefu Zhang, Haixiang Sun, Yang Xu +2
Pretrained macro-placement policies can reduce repeated optimization across circuits, but deployment often exposes them to unfamiliar designs when the original training data are un…
Selection-Aware Stress Testing for Interactive Agents
Yang Xu, Chenang Li, Jiefu Zhang +3
Agent evaluations often use one benchmark to choose a workflow and then search for task types where its advantage weakens, so both conclusions are selected from the same data. We i…
Hierarchical Multilevel Monte Carlo for Order-Optimal Neural Actor-Critic in Average-Reward CMDPs
Ankur Naskar, Vaneet Aggarwal
Constrained Markov Decision Processes (CMDPs) provide a natural framework for reinforcement learning in safety-critical applications, where agents maximize long-term reward while s…
Hypergradient-based Bilevel Reinforcement Learning with Improved Sample Complexity
Naman Saxena, Mudit Gaur, Vaneet Aggarwal
Bilevel reinforcement learning (RL) is an important framework within the literature of RL that can be used to formalize various categories of problems, such as meta-learning, hiera…
Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking
Yang Xu, Jiefu Zhang, Haixiang Sun +3
Adaptive prompt and program search makes LLM evaluation selection-sensitive. Once benchmark items are reused inside tuning, the observed winner's score need not estimate the fresh-…
Breaking the Bias Barrier in Concave Multi-Objective Reinforcement Learning
Swetha Ganesh, Vaneet Aggarwal
While standard reinforcement learning optimizes a single reward signal, many applications require optimizing a nonlinear utility over multiple objectives, wh…
Global Convergence of Average Reward Constrained MDPs with Neural Critic and General Policy Parameterization
Anirudh Satheesh, Pankaj Kumar Barman, Washim Uddin Mondal +1
We study infinite-horizon Constrained Markov Decision Processes (CMDPs) with general policy parameterizations and multi-layer neural network critics. Existing theoretical analyses…
Don't Freeze, Don't Crash: Extending the Safe Operating Range of Neural Navigation in Dense Crowds
Jiefu Zhang, Yang Xu, Vaneet Aggarwal
Navigating safely through dense crowds requires collision avoidance that generalizes beyond the densities seen during training. Learning-based crowd navigation can break under out-…
Regret Analysis of Unichain Average Reward Constrained MDPs with General Parameterization
Anirudh Satheesh, Vaneet Aggarwal
We study infinite-horizon average-reward constrained Markov decision processes (CMDPs) under the unichain assumption and general policy parameterizations. Existing regret analyses…
Persistent-Transient Policy Evaluation for Markov Chains via Minimal Peripheral Quotients
Yang Xu, Vaneet Aggarwal
We study fixed-policy evaluation for finite Markov chains that may be reducible and periodic. Classical evaluation methods with gain and bias decomposition are not always diagnosti…
Sample Complexity Analysis for Constrained Bilevel Reinforcement Learning
Naman Saxena, Vaneet Aggarwal
Several important problem settings within the literature of reinforcement learning (RL), such as meta-learning, hierarchical learning, and RL from human feedback (RL-HF), can be mo…
Order-Optimal Sample Complexity of Rectified Flows
Hari Krishna Sahoo, Mudit Gaur, Vaneet Aggarwal
Recently, flow-based generative models have shown superior efficiency compared to diffusion models. In this paper, we study rectified flow models, which constrain transport traject…
Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching
Mudit Gaur, Prashant Trivedi, Shuchin Aeron +3
Flow matching has recently emerged as a promising alternative to diffusion-based generative models, offering faster sampling and simpler training by learning continuous flows gover…
ECPv2: Fast, Efficient, and Scalable Global Optimization of Lipschitz Functions
Fares Fourati, Mohamed-Slim Alouini, Vaneet Aggarwal
We propose ECPv2, a scalable and theoretically grounded algorithm for global optimization of Lipschitz-continuous functions with unknown Lipschitz constants. Building on the Every…
Primal-Only Actor Critic Algorithm for Robust Constrained Average Cost MDPs
Anirudh Satheesh, Sooraj Sathish, Swetha Ganesh +2
In this work, we study the problem of finding robust and safe policies in Robust Constrained Average-Cost Markov Decision Processes (RCMDPs). A key challenge in this setting is the…
Distributionally Robust Self Paced Curriculum Reinforcement Learning
Anirudh Satheesh, Keenan Powell, Vaneet Aggarwal
A central challenge in reinforcement learning is that policies trained in controlled environments often fail under distribution shifts at deployment into real-world environments. D…
Discrete State Diffusion Models: A Sample Complexity Perspective
Aadithya Srikanth, Mudit Gaur, Vaneet Aggarwal
Diffusion models have demonstrated remarkable performance in generating high-dimensional samples across domains such as vision, language, and the sciences. Although continuous-stat…
Efficient Q-Learning and Actor-Critic Methods for Robust Average-Reward Reinforcement Learning
Yang Xu, Swetha Ganesh, Vaneet Aggarwal
We study model-free methods for distributionally robust infinite-horizon average-reward Markov decision processes (MDPs). We present non-asymptotic convergence analyses of Q-learni…
Regret Analysis of Average-Reward Unichain MDPs via an Actor-Critic Approach
Swetha Ganesh, Vaneet Aggarwal
Actor-Critic methods are widely used for their scalability, yet existing theoretical guarantees for infinite-horizon average-reward Markov Decision Processes (MDPs) often rely on r…
Improved Sample Complexity For Diffusion Model Training Without Empirical Risk Minimizer Access
Mudit Gaur, Prashant Trivedi, Sasidhar Kunapuli +2
Diffusion models have demonstrated state-of-the-art performance across vision, language, and scientific domains. Despite their empirical success, prior theoretical analyses of the…
Global Convergence for Average Reward Constrained MDPs with Primal-Dual Actor Critic Algorithm
Yang Xu, Swetha Ganesh, Washim Uddin Mondal +2
This paper investigates infinite-horizon average reward Constrained Markov Decision Processes (CMDPs) with general parametrization. We propose a Primal-Dual Natural Actor-Critic al…
On The Sample Complexity Bounds In Bilevel Reinforcement Learning
Mudit Gaur, Utsav Singh, Amrit Singh Bedi +2
Bilevel reinforcement learning (BRL) has emerged as a powerful framework for aligning generative models, yet its theoretical foundations, especially sample complexity bounds, remai…