arXiv research

Paper tackles online learning in large MDPs with low Bellman rank using AVE algorithm.

This paper studies systematic exploration for reinforcement learning with rich observations and function approximation. We introduce a new model called contextual decision processes, that unifies and generalizes most prior settings. Our first contribution is a complexity measure, the Bellman rank, that we show enables …

New BE dimension measure reveals rich RL problems with sample-efficient algorithms.

Efficiently samples complex distributions using tensor train format.

Survey of reinforcement learning guarantees with data constraints.

Paper studies offline RL with linear approx, focusing on inherent Bellman error.

Study shows offline RL under $Q^\star$-approximation and partial coverage is harder than previously thought.

Under a Bayesian framework, we formulate the fully sequential sampling and selection decision in statistical ranking and selection as a stochastic control problem, and derive the associated Bellman equation. Using value function approximation, we derive an approximately optimal allocation policy. We show that this poli…

Paper develops neural network approximation for pessimistic offline RL with theoretical guarantees.

Selective state-adaptive regularization improves offline RL performance.

Rank-one measurements limit feasible sets for low-rank PSD matrices.

OMLE combines optimism and MLE for efficient sequential decision making.

FedLoRU improves FL efficiency by using low-rank updates.

Low-rank modeling generally refers to a class of methods that solve problems by representing variables of interest as low-rank matrices. It has achieved great success in various fields including computer vision, data mining, signal processing and bioinformatics. Recently, much progress has been made in theories, algori…

New method solves nonsmooth low-rank matrix optimization problems efficiently.

SGD with mini-batches can solve convex low-rank matrix problems efficiently.

New spectral methods improve matrix estimation in RL with low-rank structure.

Proposes tensor Q-rank for better tensor rank recovery in complex data.

The paper proposes using low rank assumption to improve causal structure learning in DAGs.

The paper analyzes how low-rank layers in neural networks improve generalization.

Novel method for efficient low-rank matrix estimation and bandit algorithms.

Algorithm recovers multiple low-rank matrices from unlabeled data.

In this paper, we consider the problem of low-rank phase retrieval whose objective is to estimate a complex low-rank matrix from magnitude-only measurements. We propose a hierarchical prior model for low-rank phase retrieval, in which a Gaussian-Wishart hierarchical prior is placed on the underlying low-rank matrix to …

Paper improves MVSC using tensor low-rank modeling.

Derives smooth homogeneous structures for low-rank tensors.

Bayesian model improves image completion accuracy by automatically learning low rank structure.

Low-rank approximation is an effective model compression technique to not only reduce parameter storage requirements, but to also reduce computations. For convolutional neural networks (CNNs), however, well-known low-rank approximation methods, such as Tucker or CP decomposition, result in degraded model accuracy becau…

Low-rank structure emerges in neural networks during learning.

Paper tackles fair low-rank approximation and column subset selection.

Research reveals deep networks often learn low-rank structures, leading to more efficient training and fine-tuning.

New insights into training deep networks with low rank layers.

Matrices of (approximate) low rank are pervasive in data science, appearing in recommender systems, movie preferences, topic models, medical records, and genomics. While there is a vast literature on how to exploit low rank structure in these datasets, there is less attention on explaining why the low rank structure ap…

This paper tackles fitting multilevel low rank matrices by addressing three problems.

New algorithm improves deep learning models' robustness without sacrificing accuracy.

New method for initializing low-rank neural networks improves performance.

Paper develops methods for non-quadratic loss low-rank matrix recovery.

Matrix approximation is a common tool in machine learning for building accurate prediction models for recommendation systems, text mining, and computer vision. A prevalent assumption in constructing matrix approximations is that the partially observed matrix is of low-rank. We propose a new matrix approximation model w…

Unified framework for statistical inference of low-rank tensors.

We propose a low-rank approach to learning a Mahalanobis metric from data. Inspired by the recent geometric mean metric learning (GMML) algorithm, we propose a low-rank variant of the algorithm. This allows to jointly learn a low-dimensional subspace where the data reside and the Mahalanobis metric that appropriately f…

New tensor completion method reduces impact of outliers.

A low-rank tensor model simplifies multi-dimensional Markov chains.

New algorithm for weighted low rank approximation with provable guarantees.

Optimizes wide low-rank neural networks for reduced parameters and cost.

New nonconvex regularizer speeds up low-rank matrix completion.

A new method for efficient neural network fine-tuning using queryable low-rank update atoms.

We consider the problem of noisy matrix completion, in which the goal is to reconstruct a structured matrix whose entries are partially observed in noise. Standard approaches to this underdetermined inverse problem are based on assuming that the underlying matrix has low rank, or is well-approximated by a low rank matr…

In this paper, we propose a low-rank approximation method based on discrete least-squares for the approximation of a multivariate function from random, noisy-free observations. Sparsity inducing regularization techniques are used within classical algorithms for low-rank approximation in order to exploit the possible sp…

New approach to convex hulls for low-rank problems.