arXiv research

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

Algorithm solves online binary classification and infinite games using ERM oracle.

New RLHF framework handles general preference oracles without reward functions.

Quantum oracles help identify counterfactuals better than classical ones.

We consider online learning in an adversarial, non-convex setting under the assumption that the learner has an access to an offline optimization oracle. In the general setting of prediction with expert advice, Hazan et al. (2016) established that in the optimization-oracle model, online learning requires exponentially …

MAMBA learns policies competitive with multiple conflicting oracles.

Average Oracle outperforms DCC+NLS in portfolio optimization.

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…

We suggest a general oracle-based framework that captures different parallel stochastic optimization settings described by a dependency graph, and derive generic lower bounds in terms of this graph. We then use the framework and derive lower bounds for several specific parallel optimization settings, including delayed …

A major challenge in contextual bandits is to design general-purpose algorithms that are both practically useful and theoretically well-founded. We present a new technique that has the empirical and computational advantages of realizability-based approaches combined with the flexibility of agnostic methods. Our algorit…

Paper introduces structured sparsity estimators for Generalized Linear Models.

Riemannian Proximal Sampler improves sampling on manifold data.

Study on tradeoffs between mistakes and ERM oracle calls in online and transductive learning.

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…

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

Oracle-efficient algorithm for offline RL with partial data coverage.

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

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…

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

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…

Generative model improves safety in self-driving simulators and human motion generation.

New algorithm reduces online learning error for unknown feature distributions.

Oracle-efficient algorithms for online learning with smoothed and hint-adversaries.

Algorithm samples composite logconcave densities efficiently.

New oracle uses uncertainty for active classification with noisy feedback.

Method discovers symmetries in data with neural networks.

SoQal reduces oracle label requests in active learning by up to 35%.

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

GPE algorithm optimizes nonparametric contextual bandits with efficient regret bounds.

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 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…

New oracles improve stochastic optimization with noisy or biased measurements.

Develops new oracle inequalities for Gaussian ranking estimators.

New method removes oracle and reduces memory usage for robust MDPs.

A generative model may generate utter nonsense when it is fit to maximize the likelihood of observed data. This happens due to "model error," i.e., when the true data generating distribution does not fit within the class of generative models being learned. To address this, we propose a model of active distribution lear…

New algorithm learns efficiently with a simple 'yes/no' oracle.

Oracle inequalities and variable selection properties for the Lasso in linear models have been established under a variety of different assumptions on the design matrix. We show in this paper how the different conditions and concepts relate to each other. The restricted eigenvalue condition (Bickel et al., 2009) or the…

The aim of this paper is to provide some theoretical understanding of quasi-Bayesian aggregation methods non-negative matrix factorization. We derive an oracle inequality for an aggregated estimator. This result holds for a very general class of prior distributions and shows how the prior affects the rate of convergenc…

New study shows Gaussian samplers struggle with heavy-tailed targets, while stable samplers excel.

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

Study on optimal rates for sequential probability assignment using smoothed analysis.

We study the computational tractability of PAC reinforcement learning with rich observations. We present new provably sample-efficient algorithms for environments with deterministic hidden state dynamics and stochastic rich observations. These methods operate in an oracle model of computation -- accessing policy and va…

Panoptic trades options without oracles on Ethereum.

In this paper, we propose to combine imitation and reinforcement learning via the idea of reward shaping using an oracle. We study the effectiveness of the near-optimal cost-to-go oracle on the planning horizon and demonstrate that the cost-to-go oracle shortens the learner's planning horizon as function of its accurac…

Semi-supervised active clustering (SSAC) utilizes the knowledge of a domain expert to cluster data points by interactively making pairwise "same-cluster" queries. However, it is impractical to ask human oracles to answer every pairwise query. In this paper, we study the influence of allowing "not-sure" answers from a w…

Three new oracle-efficient algorithms for private synthetic data release.

Unified formulation bridges adversarial and nonstationary bandits.

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…