arXiv research

New algorithms reduce regret for convex bandits with small comparator norms.

Improves bandit convex optimization with gradient variations.

New algorithm reduces regret in stochastic bandit convex optimization.

The dueling bandit is a learning framework wherein the feedback information in the learning process is restricted to a noisy comparison between a pair of actions. In this research, we address a dueling bandit problem based on a cost function over a continuous space. We propose a stochastic mirror descent algorithm and …

Study tackles non-stationary bandit convex optimization with new algorithms.

The paper tackles minimax optimality in continuum contextual bandits with Hölder continuity.

New algorithm reduces regret in bandit optimization for high-dimensional data.

This paper improves offline contextual bandits using distributional robustness.

Unified framework for analyzing online convex optimization across various settings.

Efficient algorithm for zeroth-order bandit convex optimization with bounds on regret.

Study on collaborative vs. non-collaborative online and bandit convex optimization.

We consider the closely related problems of bandit convex optimization with two-point feedback, and zero-order stochastic convex optimization with two function evaluations per round. We provide a simple algorithm and analysis which is optimal for convex Lipschitz functions. This improves on \cite{dujww13}, which only p…

Randomized exploration in linear bandits achieves optimal regret bounds.

RONM method reduces regret in stochastic convex bandits with decreasing noise.

Motivated by applications in clinical trials and finance, we study the problem of online convex optimization (with bandit feedback) where the decision maker is risk-averse. We provide two algorithms to solve this problem. The first one is a descent-type algorithm which is easy to implement. The second algorithm, which …

Risk-aware linear bandits optimize against adverse outcomes.

Boosting improves online decision-making for large expert sets.

Paper introduces a new framework for optimizing non-convex functions.

Paper tackles LDP bandits learning with improved results and sub-linear regret.

Improved online learning for hidden-convex losses achieves optimal regret.

In this paper, we propose the first computationally efficient projection-free algorithm for bandit convex optimization (BCO). We show that our algorithm achieves a sublinear regret of $O(nT^{4/5})$ (where $T$ is the horizon and $n$ is the dimension) for any bounded convex functions with uniformly bounded gradients. We …

New lower bound shows bandit convex optimization is harder than previously thought.

New algorithm tackles heterogeneous curvature in online convex optimization.

New algorithm controls linear systems with bandit feedback, achieving optimal regret.

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

Stochastic structured prediction under bandit feedback follows a learning protocol where on each of a sequence of iterations, the learner receives an input, predicts an output structure, and receives partial feedback in form of a task loss evaluation of the predicted structure. We present applications of this learning …

SCaLE tackles dynamic regret in noisy bandit feedback with switching costs.

We construct a new map from a convex function to a distribution on its domain, with the property that this distribution is a multi-scale exploration of the function. We use this map to solve a decade-old open problem in adversarial bandit convex optimization by showing that the minimax regret for this problem is $\tild…

New algorithm controls systems with unknown, changing losses.

We consider the problem of bandit optimization, inspired by stochastic optimization and online learning problems with bandit feedback. In this problem, the objective is to minimize a global loss function of all the actions, not necessarily a cumulative loss. This framework allows us to study a very general class of pro…

We provide the first algorithm for online bandit linear optimization whose regret after T rounds is of order sqrt{Td ln N} on any finite class X of N actions in d dimensions, and of order d*sqrt{T} (up to log factors) when X is infinite. These bounds are not improvable in general. The basic idea utilizes tools from con…

Optimal algorithm finds if point is in convex hull of distributions.

New algorithms robust to adversarial data achieve optimal performance.

New algorithm for fair ranking in contextual bandits with concave rewards.

Bandit algorithms have been predominantly analyzed in the convex setting with function-value based stationary regret as the performance measure. In this paper, motivated by online reinforcement learning problems, we propose and analyze bandit algorithms for both general and structured nonconvex problems with nonstation…

Algorithms for bandit convex optimization and online learning often rely on constructing noisy gradient estimates, which are then used in appropriately adjusted first-order algorithms, replacing actual gradients. Depending on the properties of the function to be optimized and the nature of ``noise'' in the bandit feedb…

Efficient boosting method for regression with limited feedback.

PopArt efficiently solves sparse linear bandits with tighter recovery guarantees.

New algorithm DUSA minimizes regret in structured bandits with structural information.

Improved regret bound for adversarial bandit convex optimisation.

The problem of stochastic convex optimization with bandit feedback (in the learning community) or without knowledge of gradients (in the optimization community) has received much attention in recent years, in the form of algorithms and performance upper bounds. However, much less is known about the inherent complexity …

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…

Paper addresses private online convex optimization with optimal algorithms in various geometries and high-dimensional bandits.

New algorithm for online learning in episodic MDPs with convex objectives.

New algorithms for private generalized linear contextual bandits.

TRAiL is a linear bandit algorithm that ensures optimal regret and guarantees inference quality.

Simplified proof for Tsallis-INF algorithm without conjugate functions.

Saddle-point optimization problems are an important class of optimization problems with applications to game theory, multi-agent reinforcement learning and machine learning. A majority of the rich literature available for saddle-point optimization has focused on the offline setting. In this paper, we study nonstationar…