arXiv research

Optimizes sample and round complexity in adaptive sampling from multiple distributions.

AdaRound improves post-training quantization of neural networks.

Proposes a flexible tournament design combining knockout and round-robin.

New algorithms for streaming bandits with limited memory.

Adaptive sequential decision making is one of the central challenges in machine learning and artificial intelligence. In such problems, the goal is to design an interactive policy that plans for an action to take, from a finite set of $n$ actions, given some partial observations. It has been shown that in many applicat…

New algorithm reduces adaptation lag in online model selection.

Two algorithms achieve optimal regret with limited adaptivity in multinomial logistic bandits.

In this paper we study the limitations of parallelization in convex optimization. A convenient approach to study parallelization is through the prism of \emph{adaptivity} which is an information theoretic measure of the parallel runtime of an algorithm [BS18]. Informally, adaptivity is the number of sequential rounds a…

Efficient methods reduce projections in non-stationary online learning.

Optimizes biomolecular simulations by ranking adaptive sampling policies.

We study an extension of the classic stochastic multi-armed bandit problem which involves multiple plays and Markovian rewards in the rested bandits setting. In order to tackle this problem we consider an adaptive allocation rule which at each stage combines the information from the sample means of all the arms, with t…

We study Online Convex Optimization in the unbounded setting where neither predictions nor gradient are constrained. The goal is to simultaneously adapt to both the sequence of gradients and the comparator. We first develop parameter-free and scale-free algorithms for a simplified setting with hints. We present two ver…

We present an adaptive online gradient descent algorithm to solve online convex optimization problems with long-term constraints , which are constraints that need to be satisfied when accumulated over a finite number of rounds T , but can be violated in intermediate rounds. For some user-defined trade-off parameter $β$…

Adapts Exp3 to adversarial bandits with delays and data.

Dynamic SBI improves SBI efficiency without rounds, reducing simulation and training costs.

New algorithm achieves near-optimal performance in dueling bandit problem.

We introduce the community exploration problem that has many real-world applications such as online advertising. In the problem, an explorer allocates limited budget to explore communities so as to maximize the number of members he could meet. We provide a systematic study of the community exploration problem, from off…

New method achieves both universality and adaptivity in online convex optimization.

DynBRO learns robustly from dynamic Byzantine workers.

aLTT selects hyperparameters efficiently with statistical guarantees.

Delaytron learns multi-class classifiers with delayed feedbacks, achieving efficient regret bounds.

The paper ranks experts based on task performance with noisy evaluations.

We propose a simple yet powerful framework for modeling integer-valued data, such as counts, scores, and rounded data. The data-generating process is defined by Simultaneously Transforming and Rounding (STAR) a continuous-valued process, which produces a flexible family of integer-valued distributions capable of modeli…

Efficient algorithms for contextual slate bandits with limited adaptivity.

We consider the problem of learning a general graph $G=(V,E)$ using edge-detecting queries, where the number of vertices $|V|=n$ is given to the learner. The information theoretic lower bound gives $m\log n$ for the number of queries, where $m=|E|$ is the number of edges. In case the number of edges $m$ is also given t…

New algorithm reduces heavy-tailed linear bandits' computational cost.

This paper solves the best arm identification problem with both quick commitment and reward maximization.

We propose the first fully-adaptive algorithm for pure exploration in linear bandits---the task to find the arm with the largest expected reward, which depends on an unknown parameter linearly. While existing methods partially or entirely fix sequences of arm selections before observing rewards, our method adaptively c…

In this paper we describe a new algorithm called Fast Adaptive Sequencing Technique (FAST) for maximizing a monotone submodular function under a cardinality constraint $k$ whose approximation ratio is arbitrarily close to $1-1/e$, is $O(\log(n) \log^2(\log k))$ adaptive, and uses a total of $O(n \log\log(k))$ queries. …

Paper tackles concept drift in Federated Learning, improving model performance.

Adaptive policies solve a linear program to maximize rewards while minimizing costs in sales with discounts.

New algorithm reduces dynamic regret in time-varying movement costs.

We consider the stochastic multi-armed bandit (MAB) problem in a setting where a player can pay to pre-observe arm rewards before playing an arm in each round. Apart from the usual trade-off between exploring new arms to find the best one and exploiting the arm believed to offer the highest reward, we encounter an addi…

We study online linear regression problems in a distributed setting, where the data is spread over a network. In each round, each network node proposes a linear predictor, with the objective of fitting the \emph{network-wide} data. It then updates its predictor for the next round according to the received local feedbac…

This paper tackles combinatorial pure exploration for dueling bandits, aiming to find the best candidate-position match.

Improved algorithm for adaptive dueling bandits with near-optimal regret bound.

We consider the problem of probably approximately correct (PAC) ranking $n$ items by adaptively eliciting subset-wise preference feedback. At each round, the learner chooses a subset of $k$ items and observes stochastic feedback indicating preference information of the winner (most preferred) item of the chosen subset …

A fast algorithm for $K$-means clustering using subsampled SDP.

Communication overhead is one of the key challenges that hinders the scalability of distributed optimization algorithms. In this paper, we study local distributed SGD, where data is partitioned among computation nodes, and the computation nodes perform local updates with periodically exchanging the model among the work…

Near-optimal per-action regret bounds for sleeping bandits are derived.

New algorithm resists corruption in linear contextual bandits.

We consider the problem of adaptively placing sensors along an interval to detect stochastically-generated events. We present a new formulation of the problem as a continuum-armed bandit problem with feedback in the form of partial observations of realisations of an inhomogeneous Poisson process. We design a solution m…

Streaming algorithms are generally judged by the quality of their solution, memory footprint, and computational complexity. In this paper, we study the problem of maximizing a monotone submodular function in the streaming setting with a cardinality constraint $k$. We first propose Sieve-Streaming++, which requires just…

We study the problem of estimating a set of $d$ linear queries with respect to some unknown distribution $\mathbf{p}$ over a domain $\mathcal{J}=[J]$ based on a sensitive data set of $n$ individuals under the constraint of local differential privacy. This problem subsumes a wide range of estimation tasks, e.g., distrib…

New algorithm reduces regret for linear bandits with unknown noise variance.

We study a basic private estimation problem: each of $n$ users draws a single i.i.d. sample from an unknown Gaussian distribution, and the goal is to estimate the mean of this Gaussian distribution while satisfying local differential privacy for each user. Informally, local differential privacy requires that each data …

Algorithm allocates perishable resources online to minimize envy and inefficiency.

To deal with changing environments, a new performance measure -- adaptive regret, defined as the maximum static regret over any interval, was proposed in online learning. Under the setting of online convex optimization, several algorithms have been successfully developed to minimize the adaptive regret. However, existi…