Breaking the sample size barrier in model-based reinforcement learning with a generative model
We investigate the sample efficiency of reinforcement learning in a $\gamma $-discounted
infinite-horizon Markov decision process (MDP) with state space S and action space A …
infinite-horizon Markov decision process (MDP) with state space S and action space A …
The power of preconditioning in overparameterized low-rank matrix sensing
Abstract We propose $\textsf {ScaledGD ($\lambda $)} $, a preconditioned gradient descent
method to tackle the low-rank matrix sensing problem when the true rank is unknown, and …
method to tackle the low-rank matrix sensing problem when the true rank is unknown, and …
Approximate message passing from random initialization with applications to Z2 synchronization
This paper is concerned with the problem of reconstructing an unknown rank-one matrix with
prior structural information from noisy observations. While computing the Bayes optimal …
prior structural information from noisy observations. While computing the Bayes optimal …
A theory of non-linear feature learning with one gradient step in two-layer neural networks
Feature learning is thought to be one of the fundamental reasons for the success of deep
neural networks. It is rigorously known that in two-layer fully-connected neural networks …
neural networks. It is rigorously known that in two-layer fully-connected neural networks …
A non-asymptotic framework for approximate message passing in spiked models
Approximate message passing (AMP) emerges as an effective iterative paradigm for solving
high-dimensional statistical problems. However, prior AMP theory--which focused mostly on …
high-dimensional statistical problems. However, prior AMP theory--which focused mostly on …
[HTML][HTML] Bridging convex and nonconvex optimization in robust PCA: Noise, outliers, and missing data
This paper delivers improved theoretical guarantees for the convex programming approach
in low-rank matrix estimation, in the presence of (1) random noise,(2) gross sparse outliers …
in low-rank matrix estimation, in the presence of (1) random noise,(2) gross sparse outliers …
Scaling and scalability: Provable nonconvex low-rank tensor estimation from incomplete measurements
Tensors, which provide a powerful and flexible model for representing multi-attribute data
and multi-way interactions, play an indispensable role in modern data science across …
and multi-way interactions, play an indispensable role in modern data science across …
Model-based reinforcement learning is minimax-optimal for offline zero-sum markov games
This paper makes progress towards learning Nash equilibria in two-player zero-sum Markov
games from offline data. Specifically, consider a $\gamma $-discounted infinite-horizon …
games from offline data. Specifically, consider a $\gamma $-discounted infinite-horizon …
Extending relax-and-round combinatorial optimization solvers with quantum correlations
We introduce a relax-and-round approach embedding the quantum approximate
optimization algorithm (QAOA) with p≥ 1 layers. We show for many problems, including …
optimization algorithm (QAOA) with p≥ 1 layers. We show for many problems, including …
Learning mixtures of linear dynamical systems
Y Chen, HV Poor - International conference on machine …, 2022 - proceedings.mlr.press
We study the problem of learning a mixture of multiple linear dynamical systems (LDSs) from
unlabeled short sample trajectories, each generated by one of the LDS models. Despite the …
unlabeled short sample trajectories, each generated by one of the LDS models. Despite the …