Search Results for author:
Found 32 papers, 7 papers with code
Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank Bandits
Assuming access to the distribution of the covariates, we propose a novel low-rank matrix estimation method called LowPopArt and provide its recovery guarantee that depends on a novel quantity denoted by B(Q) that characterizes the hardness of the problem, where Q is the covariance matrix of the measurement distribution.
Better-than-KL PAC-Bayes Bounds
In this paper, we consider the problem of proving concentration inequalities to estimate the mean of the sequence.
Noise-Adaptive Confidence Sets for Linear Bandits and Application to Bayesian Optimization
First, we propose a novel confidence set that is `semi-adaptive' to the unknown sub-Gaussian parameter $\sigma_*^2$ in the sense that the (normalized) confidence width scales with $\sqrt{d\sigma_*^2 + \sigma_0^2}$ where $d$ is the dimension and $\sigma_0^2$ is the specified sub-Gaussian parameter (known) that can be much larger than $\sigma_*^2$.
Graph Sparsifications using Neural Network Assisted Monte Carlo Tree Search
Graph neural networks have been successful for machine learning, as well as for combinatorial and graph problems such as the Subgraph Isomorphism Problem and the Traveling Salesman Problem.
Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion
Logistic bandit is a ubiquitous framework of modeling users' choices, e. g., click vs. no click for advertisement recommender system.
Nearly Optimal Steiner Trees using Graph Neural Network Assisted Monte Carlo Tree Search
Graph neural networks are useful for learning problems, as well as for combinatorial and graph problems such as the Subgraph Isomorphism Problem and the Traveling Salesman Problem.
Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded Rewards
Maillard sampling \cite{maillard13apprentissage}, an attractive alternative to Thompson sampling, has recently been shown to achieve competitive regret guarantees in the sub-Gaussian reward setting \cite{bian2022maillard} while maintaining closed-form action probabilities, which is useful for offline policy evaluation.
Tighter PAC-Bayes Bounds Through Coin-Betting
We consider the problem of estimating the mean of a sequence of random elements $f(X_1, \theta)$ $, \ldots, $ $f(X_n, \theta)$ where $f$ is a fixed scalar function, $S=(X_1, \ldots, X_n)$ are independent random variables, and $\theta$ is a possibly $S$-dependent parameter.
Revisiting Simple Regret: Fast Rates for Returning a Good Arm
Simple regret is a natural and parameter-free performance criterion for pure exploration in multi-armed bandits yet is less popular than the probability of missing the best arm or an $\epsilon$-good arm, perhaps due to lack of easy ways to characterize it.
PopArt: Efficient Sparse Regression and Experimental Design for Optimal Sparse Linear Bandits
In this paper, we propose a simple and computationally efficient sparse linear estimation method called PopArt that enjoys a tighter $\ell_1$ recovery guarantee compared to Lasso (Tibshirani, 1996) in many problems.
Norm-Agnostic Linear Bandits
For the latter, we do not pay any price in the regret for now knowing $S$.
An Experimental Design Approach for Regret Minimization in Logistic Bandits
Finally, we discuss the impact of the bias of the MLE on the logistic bandit problem, providing an example where $d^2$ lower order regret (cf., it is $d$ for linear bandits) may not be improved as long as the MLE is used and how bias-corrected estimators may be used to make it closer to $d$.
Jointly Efficient and Optimal Algorithms for Logistic Bandits
Logistic Bandits have recently undergone careful scrutiny by virtue of their combined theoretical and practical relevance.
Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPs
For linear bandits, we achieve $\tilde O(\min\{d\sqrt{K}, d^{1. 5}\sqrt{\sum_{k=1}^K \sigma_k^2}\} + d^2)$ where $d$ is the dimension of the features, $K$ is the time horizon, and $\sigma_k^2$ is the noise variance at time step $k$, and $\tilde O$ ignores polylogarithmic dependence, which is a factor of $d^3$ improvement.
Maillard Sampling: Boltzmann Exploration Done Optimally
This less-known algorithm, which we call Maillard sampling (MS), computes the probability of choosing each arm in a \textit{closed form}, which is not true for Thompson sampling, a widely-adopted bandit algorithm in the industry.
Tight Concentrations and Confidence Sequences from the Regret of Universal Portfolio
A classic problem in statistics is the estimation of the expectation of random variables from samples.
Transfer Learning in Bandits with Latent Continuity
To cope with the latent structural parameter, we consider a transfer learning setting in which an agent must learn to transfer the structural information from the prior tasks to the next task, which is inspired by practical problems such as rate adaptation in wireless link.
DISE: Dynamic Integrator Selection to Minimize Forward Pass Time in Neural ODEs
Because it is not the case that every input requires the advanced integrator, we design an auxiliary neural network to choose an appropriate integrator given input to decrease the overall inference time without significantly sacrificing accuracy.
Improved Confidence Bounds for the Linear Logistic Model and Applications to Linear Bandits
Specifically, our confidence bound avoids a direct dependence on $1/\kappa$, where $\kappa$ is the minimal variance over all arms' reward distributions.
Crush Optimism with Pessimism: Structured Bandits Beyond Asymptotic Optimality
In this paper, we focus on the finite hypothesis case and ask if one can achieve the asymptotic optimality while enjoying bounded regret whenever possible.
Parameter-Free Locally Differentially Private Stochastic Subgradient Descent
We consider the problem of minimizing a convex risk with stochastic subgradients guaranteeing $\epsilon$-locally differentially private ($\epsilon$-LDP).
Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration
In this paper, we consider the nonparametric least square regression in a Reproducing Kernel Hilbert Space (RKHS).
Parameter-Free Online Convex Optimization with Sub-Exponential Noise
We show that BANCO achieves the optimal regret rate in our problem.
Bilinear Bandits with Low-rank Structure
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.
Adversarial Attacks on Stochastic Bandits
We study adversarial attacks that manipulate the reward signals to control the actions chosen by a stochastic multi-armed bandit algorithm.
Data Poisoning Attacks in Contextual Bandits
We provide a general attack framework based on convex optimization and show that by slightly manipulating rewards in the data, an attacker can force the bandit algorithm to pull a target arm for a target contextual vector.
Online Learning for Changing Environments using Coin Betting
A key challenge in online learning is that classical algorithms can be slow to adapt to changing environments.
Scalable Generalized Linear Bandits: Online Computation and Hashing
Second, for the case where the number $N$ of arms is very large, we propose new algorithms in which each next arm is selected via an inner product search.
Improved Strongly Adaptive Online Learning using Coin Betting
This paper describes a new parameter-free online learning algorithm for changing environments.
Graph-Based Active Learning: A New Look at Expected Error Minimization
In graph-based active learning, algorithms based on expected error minimization (EEM) have been popular and yield good empirical performance.
Human Memory Search as Initial-Visit Emitting Random Walk
In this paper, we propose the first efficient maximum likelihood estimate (MLE) for INVITE by decomposing the censored output into a series of absorbing random walks.
