arXiv research

MAMBA learns policies competitive with multiple conflicting oracles.

MAPS and MAPS-SE learn from multiple suboptimal experts to improve policies efficiently.

An algorithm learns from multiple models to match an oracle's risk.

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 method improves transductive learning predictions with multiplicative oracle inequalities.

We presented Bayesian portfolio selection strategy, via the $k$ factor asset pricing model. If the market is information efficient, the proposed strategy will mimic the market; otherwise, the strategy will outperform the market. The strategy depends on the selection of a portfolio via Bayesian multiple testing methodol…

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…

ConfHit provides valid guarantees for generative models without oracle access.

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

Method discovers symmetries in data with neural networks.

New algorithms estimate matrix norms without matrix multiplication.

Study on costs of manipulating AMM-based price oracles.

Study sets a nontrivial upper limit on return forecasting accuracy.

Extends covariance estimation with multiple targets for better performance.

New active learning method for kernel selection improves efficiency and accuracy.

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 …

We address the problem of learning in an online setting where the learner repeatedly observes features, selects among a set of actions, and receives reward for the action taken. We provide the first efficient algorithm with an optimal regret. Our algorithm uses a cost sensitive classification learner as an oracle and h…

Improved cutting plane method for convex optimization and games.

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…

We study the Nonparametric Maximum Likelihood Estimator (NPMLE) for estimating Gaussian location mixture densities in $d$-dimensions from independent observations. Unlike usual likelihood-based methods for fitting mixtures, NPMLEs are based on convex optimization. We prove finite sample results on the Hellinger accurac…

With recent advances in high throughput technology, researchers often find themselves running a large number of hypothesis tests (thousands+) and esti- mating a large number of effect-sizes. Generally there is particular interest in those effects estimated to be most extreme. Unfortunately naive estimates of these effe…

It is not easy to design and run Convolutional Neural Networks (CNNs) due to: 1) finding the optimal number of filters (i.e., the width) at each layer is tricky, given an architecture; and 2) the computational intensity of CNNs impedes the deployment on computationally limited devices. Oracle Pruning is designed to rem…

Neural-$σ^2$-LinearUCB improves regret in neural contextual bandits.

We address the challenge of designing optimal adversarial noise algorithms for settings where a learner has access to multiple classifiers. We demonstrate how this problem can be framed as finding strategies at equilibrium in a two-player, zero-sum game between a learner and an adversary. In doing so, we illustrate the…

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

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

The paper addresses fairness in online learning by extending auditing schemes and presenting efficient algorithms.

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

Many machine learning tasks such as clustering, classification, and dataset search benefit from embedding data points in a space where distances reflect notions of relative similarity as perceived by humans. A common way to construct such an embedding is to request triplet similarity queries to an oracle, comparing two…

New oracle uses uncertainty for active classification with noisy feedback.

Quantum oracles help identify counterfactuals better than classical ones.

Crowdsourcing has become an effective and popular tool for human-powered computation to label large datasets. Since the workers can be unreliable, it is common in crowdsourcing to assign multiple workers to one task, and to aggregate the labels in order to obtain results of high quality. In this paper, we provide finit…

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

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

Active learning selects most informative unlabeled samples for labeling.

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 …

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

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

Average Oracle outperforms DCC+NLS in portfolio optimization.

A new method solves variational inequality problems with multiple constraints without needing optimal Lagrange multipliers.

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

Method selects valid IVs from a large set using clustering and test of overidentifying restrictions.

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

FPML algorithm reduces regret by limiting the number of arms chosen per round.

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.