arXiv research

New analysis shows Thompson Sampling can work with greedy approximations in combinatorial bandits.

Paper addresses online alignment of large language models under uncertain preference feedback.

We consider the problem of minimizing the sum of submodular set functions assuming minimization oracles of each summand function. Most existing approaches reformulate the problem as the convex minimization of the sum of the corresponding Lovász extensions and the squared Euclidean norm, leading to algorithms requiring …

We study the problem of interactively learning a binary classifier using noisy labeling and pairwise comparison oracles, where the comparison oracle answers which one in the given two instances is more likely to be positive. Learning from such oracles has multiple applications where obtaining direct labels is harder bu…

Folded concave penalization methods have been shown to enjoy the strong oracle property for high-dimensional sparse estimation. However, a folded concave penalization problem usually has multiple local solutions and the oracle property is established only for one of the unknown local solutions. A challenging fundamenta…

Oracle-efficient algorithms reduce combinatorial semi-bandit regret to logarithmic time.

Gradient descent is efficient for solving feasibility problems with minimal memory and queries.

We develop theory for using heuristics to solve computationally hard problems in differential privacy. Heuristic approaches have enjoyed tremendous success in machine learning, for which performance can be empirically evaluated. However, privacy guarantees cannot be evaluated empirically, and must be proven --- without…

We revisit the question of reducing online learning to approximate optimization of the offline problem. In this setting, we give two algorithms with near-optimal performance in the full information setting: they guarantee optimal regret and require only poly-logarithmically many calls to the approximation oracle per it…

Study improves CTS's approximation regret for combinatorial bandits.

New algorithm finds k-centers from noisy distance estimates.

Develops accelerated fixed-point methods with delayed oracles for scientific computing.

We define and study the problem of modular concept learning, that is, learning a concept that is a cross product of component concepts. If an element's membership in a concept depends solely on it's membership in the components, learning the concept as a whole can be reduced to learning the components. We analyze this …

Study exact partition recovery with same-cluster oracle, bounded error.

Quantum oracles help identify counterfactuals better than classical ones.

New algorithms adapt to friendly environments in online learning.

We investigate active learning with access to two distinct oracles: Label (which is standard) and Search (which is not). The Search oracle models the situation where a human searches a database to seed or counterexample an existing solution. Search is stronger than Label while being natural to implement in many situati…

New lower bounds for bilevel optimization with first-order oracles.

Unified theory for UCB policies in total and max bandit problems.

Algorithm identifies nearest mode in noisy data.

Study reconstructs causal graph from latent variables using mixture oracles.

This paper tackles bandit optimization with a new pairwise comparison oracle for unknown strongly concave functions.

Study phase transitions in shuffled regression problems.

We investigate properties of estimators obtained by minimization of U-processes with the Lasso penalty in high-dimensional settings. Our attention is focused on the ranking problem that is popular in machine learning. It is related to guessing the ordering between objects on the basis of their observed predictors. We p…

New algorithms solve stochastic variational inequalities without bounded variance assumption.

New algorithm learns POMDPs without computational oracles.

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

New algorithm reduces super-arm selection complexity exponentially.

We note that known methods achieving the optimal oracle complexity for first order convex optimization require quadratic memory, and ask whether this is necessary, and more broadly seek to characterize the minimax number of first order queries required to optimize a convex Lipschitz function subject to a memory constra…

Lower bounds found for nonconvex-strongly-concave min-max optimization problems.

We consider the problem of adaptively PAC-learning a probability distribution $\mathcal{P}$'s mode by querying an oracle for information about a sequence of i.i.d. samples $X_1, X_2, \ldots$ generated from $\mathcal{P}$. We consider two different query models: (a) each query is an index $i$ for which the oracle reveals…

We present a probabilistic modeling framework and adaptive sampling algorithm wherein unsupervised generative models are combined with black box predictive models to tackle the problem of input design. In input design, one is given one or more stochastic "oracle" predictive functions, each of which maps from the input …

Simplifies online learning with consistent oracle to fewer mistakes.

Optimizes bilevel empirical risk minimization with improved oracle calls.

Study on gradient complexity of private optimization with private oracles.

The key issue in Dynamic Ensemble Selection (DES) is defining a suitable criterion for calculating the classifiers' competence. There are several criteria available to measure the level of competence of base classifiers, such as local accuracy estimates and ranking. However, using only one criterion may lead to a poor …

Develops algorithms for multi-class Neyman-Pearson classification with cost sensitivity.

New research shows label refinement and weak training have limitations for aligning LLMs.

New research shows fixed-budget best-arm identification cannot match static oracle performance.

$Q$-learning with function approximation is one of the most popular methods in reinforcement learning. Though the idea of using function approximation was proposed at least 60 years ago, even in the simplest setup, i.e, approximating $Q$-functions with linear functions, it is still an open problem on how to design a pr…

In this paper, we initiate a rigorous theoretical study of clustering with noisy queries (or a faulty oracle). Given a set of $n$ elements, our goal is to recover the true clustering by asking minimum number of pairwise queries to an oracle. Oracle can answer queries of the form : "do elements $u$ and $v$ belong to the…

New algorithms sample convex bodies using Markov chains and restricted Gaussian oracles.

MAMBA learns policies competitive with multiple conflicting oracles.

Probabilistic Bisection Algorithm performs root finding based on knowledge acquired from noisy oracle responses. We consider the generalized PBA setting (G-PBA) where the statistical distribution of the oracle is unknown and location-dependent, so that model inference and Bayesian knowledge updating must be performed s…

We discuss the problem of adaptive discrete-time signal denoising in the situation where the signal to be recovered admits a "linear oracle" -- an unknown linear estimate that takes the form of convolution of observations with a time-invariant filter. It was shown by Juditsky and Nemirovski (2009) that when the $\ell_2…

Improved algorithm for contextual bandits with reduced regret.

Estimates heavy hitters in data streams with queries, balancing accuracy and efficiency.

New algorithms achieve small prediction regret for learning from overlapping groups.