67 citations · 145 across the 35 of their papers we have counts for
36 papers
When Less is Enough: Efficient Inference via Collaborative Reasoning
Yilei Chen, Sharut Gupta, Yannis Paschalidis +2
In this work, we introduce DUET (Dual-model Efficient Two-stage inference), a collaborative inference framework in which a capable model and a lightweight model work together to so…
Evaluation without Generation: Non-Generative Assessment of Harmful Model Specialization with Applications to CSAM
Vinith M. Suriyakumar, Ayush Sekhari, Lena Stempfle +5
Auditing the fine-tunes of open-weight generative models for harmful specialization has become a new governance challenge for model hosting platforms. The standard toolkit, generat…
The Space Complexity of Learning-Unlearning Algorithms
Yeshwanth Cherapanamjeri, Sumegha Garg, Nived Rajaraman +2
We study the memory complexity of machine unlearning algorithms that provide strong data deletion guarantees to the users. Formally, consider an algorithm for a particular learning…
UCD: Unlearning in LLMs via Contrastive Decoding
Vinith M. Suriyakumar, Ayush Sekhari, Ashia Wilson
Machine unlearning aims to remove specific information, e.g. sensitive or undesirable content, from large language models (LLMs) while preserving overall performance. We propose an…
System-Aware Unlearning Algorithms: Use Lesser, Forget Faster
Linda Lu, Ayush Sekhari, Karthik Sridharan
Machine unlearning addresses the problem of updating a machine learning model/system trained on a dataset so that the influence of a set of deletion requests on…
The Gaussian Mixing Mechanism: Renyi Differential Privacy via Gaussian Sketches
Omri Lev, Vishwak Srinivasan, Moshe Shenfeld +3
Gaussian sketching, which consists of pre-multiplying the data with a random Gaussian matrix, is a widely used technique for multiple problems in data science and machine learning,…
The Role of Environment Access in Agnostic Reinforcement Learning
Akshay Krishnamurthy, Gene Li, Ayush Sekhari
We study Reinforcement Learning (RL) in environments with large state spaces, where function approximation is required for sample-efficient learning. Departing from a long history…
GaussMark: A Practical Approach for Structural Watermarking of Language Models
Adam Block, Ayush Sekhari, Alexander Rakhlin
Recent advances in Large Language Models (LLMs) have led to significant improvements in natural language processing tasks, but their ability to generate human-quality text raises s…
Unstable Unlearning: The Hidden Risk of Concept Resurgence in Diffusion Models
Vinith M. Suriyakumar, Rohan Alur, Ayush Sekhari +2
Text-to-image diffusion models rely on massive, web-scale datasets. Training them from scratch is computationally expensive, and as a result, developers often prefer to make increm…
Langevin Dynamics: A Unified Perspective on Optimization via Lyapunov Potentials
August Y. Chen, Ayush Sekhari, Karthik Sridharan
We study the problem of non-convex optimization using Stochastic Gradient Langevin Dynamics (SGLD). SGLD is a natural and popular variation of stochastic gradient descent where at…
Random Latent Exploration for Deep Reinforcement Learning
Srinath Mahankali, Zhang-Wei Hong, Ayush Sekhari +2
We introduce Random Latent Exploration (RLE), a simple yet effective exploration strategy in reinforcement learning (RL). On average, RLE outperforms noise-based methods, which per…
Machine Unlearning Fails to Remove Data Poisoning Attacks
Martin Pawelczyk, Jimmy Z. Di, Yiwei Lu +3
We revisit the efficacy of several practical methods for approximate machine unlearning developed for large-scale deep learning. In addition to complying with data deletion request…
Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics
Runzhe Wu, Ayush Sekhari, Akshay Krishnamurthy +1
We study computationally and statistically efficient Reinforcement Learning algorithms for the linear Bellman Complete setting. This setting uses linear function approximation to c…
Offline Reinforcement Learning: Role of State Aggregation and Trajectory Data
Zeyu Jia, Alexander Rakhlin, Ayush Sekhari +1
We revisit the problem of offline reinforcement learning with value function realizability but without Bellman completeness. Previous work by Xie and Jiang (2021) and Foster et al.…
Harnessing Density Ratios for Online Reinforcement Learning
Philip Amortila, Dylan J. Foster, Nan Jiang +2
The theories of offline and online reinforcement learning, despite having evolved in parallel, have begun to show signs of the possibility for a unification, with algorithms and an…
Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees
Yifei Zhou, Ayush Sekhari, Yuda Song +1
Hybrid RL is the setting where an RL agent has access to both offline data and online data by interacting with the real-world environment. In this work, we propose a new hybrid RL…
When is Agnostic Reinforcement Learning Statistically Tractable?
Zeyu Jia, Gene Li, Alexander Rakhlin +2
We study the problem of agnostic PAC reinforcement learning (RL): given a policy class , how many rounds of interaction with an unknown MDP (with a potentially large state and a…
Selective Sampling and Imitation Learning via Online Regression
Ayush Sekhari, Karthik Sridharan, Wen Sun +1
We consider the problem of Imitation Learning (IL) by actively querying noisy expert for feedback. While imitation learning has been empirically successful, much of prior work assu…
Ticketed Learning-Unlearning Schemes
Badih Ghazi, Pritish Kamath, Ravi Kumar +3
We consider the learning--unlearning paradigm defined as follows. First given a dataset, the goal is to learn a good predictor, such as one minimizing a certain loss. Subsequently,…
Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
Jimmy Z. Di, Jack Douglas, Jayadev Acharya +2
We introduce camouflaged data poisoning attacks, a new attack vector that arises in the context of machine unlearning and other settings when model retraining may be induced. An ad…
Model-Free Reinforcement Learning with the Decision-Estimation Coefficient
Dylan J. Foster, Noah Golowich, Jian Qian +2
We consider the problem of interactive decision making, encompassing structured bandits and reinforcement learning with general function approximation. Recently, Foster et al. (202…
From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent
Satyen Kale, Jason D. Lee, Chris De Sa +2
Stochastic Gradient Descent (SGD) has been the method of choice for learning large-scale non-convex models. While a general analysis of when SGD works has been elusive, there has b…
Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient
Yuda Song, Yifei Zhou, Ayush Sekhari +3
We consider a hybrid reinforcement learning setting (Hybrid RL), in which an agent has access to an offline dataset and the ability to collect experience via real-world online inte…
On the Complexity of Adversarial Decision Making
Dylan J. Foster, Alexander Rakhlin, Ayush Sekhari +1
A central problem in online learning and decision making -- from bandits to reinforcement learning -- is to understand what modeling assumptions lead to sample-efficient learning g…