165 citations · 950 across the 71 of their papers we have counts for
29 papers · 1 filter
The tractability landscape of diffusion alignment: regularization, rewards, and computational primitives
Ankur Moitra, Andrej Risteski, Dhruv Rohatgi
Inference-time reward alignment asks how to turn a pre-trained diffusion model with base law into a sampler that favors a reward while remaining close to . Since there i…
Model Stealing for Any Low-Rank Language Model
Allen Liu, Ankur Moitra
Model stealing, where a learner tries to recover an unknown model via carefully chosen queries, is a critical problem in machine learning, as it threatens the security of proprieta…
Bypassing the Noisy Parity Barrier: Learning Higher-Order Markov Random Fields from Dynamics
Jason Gaitonde, Ankur Moitra, Elchanan Mossel
We consider the problem of learning graphical models, also known as Markov random fields (MRFs) from temporally correlated samples. As in many traditional statistical settings, fun…
Exploration is Harder than Prediction: Cryptographically Separating Reinforcement Learning from Supervised Learning
Noah Golowich, Ankur Moitra, Dhruv Rohatgi
Supervised learning is often computationally easy in practice. But to what extent does this mean that other modes of learning, such as reinforcement learning (RL), ought to be comp…
Exploring and Learning in Sparse Linear MDPs without Computationally Intractable Oracles
Noah Golowich, Ankur Moitra, Dhruv Rohatgi
The key assumption underlying linear Markov Decision Processes (MDPs) is that the learner has access to a known feature map that maps state-action pairs to -dimensiona…
Tensor Decompositions Meet Control Theory: Learning General Mixtures of Linear Dynamical Systems
Ainesh Bakshi, Allen Liu, Ankur Moitra +1
Recently Chen and Poor initiated the study of learning mixtures of linear dynamical systems. While linear dynamical systems already have wide-ranging applications in modeling time-…