arXiv research

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

An algorithm tackles low-rank linear bandit problems with improved regret bounds.

Paper introduces G-LowTESTR for efficient tensor bandits.

The paper tackles pure exploration in multi-armed bandits with low rank structure using oblivious sampling.

Develops TOFU for tensor bandits with low-rank structure.

Unified approach tackles high-dimensional tensor bandits with convex optimization and weakly decomposable regularizers.

Introduces tensor bandits for multi-dimensional online decision making.

Efficient algorithms for low-rank bandits using subspace recovery.

Paper presents a reduction-based framework for conservative bandits and RL with improved lower and upper bounds.

New algorithm tackles dynamic query routing to multiple embedding models.

New algorithm catches moving subspaces in bandit problems.

We introduce the bilinear bandit problem with low-rank structure in which an action takes the form of a pair of arms from two different entity types, and the reward is a bilinear function of the known feature vectors of the arms. The unknown in the problem is a $d_1$ by $d_2$ matrix $\mathbfΘ^*$ that defines the reward…

Algorithm for low-rank matrix bandits with heavy-tailed rewards, achieving nearly optimal regret bound.

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

New algorithms minimize regret in multi-task and lifelong linear bandits with shared representation.

New framework improves efficiency in low-rank matrix bandit problems.

Study multi-task learning with low-rank representation in stochastic linear bandits.

Optimizes algorithms for non-concave bandit problems.

High-dimensional representations often have a lower dimensional underlying structure. This is particularly the case in many decision making settings. For example, when the representation of actions is generated from a deep neural network, it is reasonable to expect a low-rank structure whereas conventional structures l…

We consider dynamic pricing with many products under an evolving but low-dimensional demand model. Assuming the temporal variation in cross-elasticities exhibits low-rank structure based on fixed (latent) features of the products, we show that the revenue maximization problem reduces to an online bandit convex optimiza…

Unified framework for high-dimensional bandit problems with low-dimensional structures.

New algorithm improves learning efficiency in multi-task contextual bandits.

New method for online low-rank matrix completion with improved regret.

A new framework for structured bandits using influence diagrams and variational Thompson sampling.

Jointly tackles assortment and pricing in retail, using bandit models.

Algorithm achieves comparable performance to fully dynamic data with only a few batches.

GL-LowPopArt improves minimax-optimal estimation for trace regression.

Improved regret bounds for structured linear contextual bandits with Gaussian noise.

A new algorithm reduces the time and space complexity for multinomial logistic bandits.

Many problems in computer vision and recommender systems involve low-rank matrices. In this work, we study the problem of finding the maximum entry of a stochastic low-rank matrix from sequential observations. At each step, a learning agent chooses pairs of row and column arms, and receives the noisy product of their l…

New algorithms use offline data to improve online decision-making with latent states.

Efficiently learns neural network parameters from streaming data.

New algorithm reduces cold-start costs in multi-armed bandits for many products.

We consider a stochastic continuum armed bandit problem where the arms are indexed by the $\ell_2$ ball $B_{d}(1+ν)$ of radius $1+ν$ in $\mathbb{R}^d$. The reward functions $r :B_{d}(1+ν) \rightarrow \mathbb{R}$ are considered to intrinsically depend on $k \ll d$ unknown linear parameters so that $r(\mathbf{x}) = g(\ma…

The stochastic linear bandit problem proceeds in rounds where at each round the algorithm selects a vector from a decision set after which it receives a noisy linear loss parameterized by an unknown vector. The goal in such a problem is to minimize the (pseudo) regret which is the difference between the total expected …

Gaussian processes (GP) are a well studied Bayesian approach for the optimization of black-box functions. Despite their effectiveness in simple problems, GP-based algorithms hardly scale to high-dimensional functions, as their per-iteration time and space cost is at least quadratic in the number of dimensions $d$ and i…

This paper explains why distributional reinforcement learning is better than vanilla RL using small-loss bounds.

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…

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

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.

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…

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

Algorithm recovers multiple low-rank matrices from unlabeled data.

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.

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