arXiv research

Study finds on-chain data can proxy off-chain cryptocurrency pricing.

Non-negative curvature affects Markov chains' mixing and expansion properties.

We investigate the disparity between smooth and topological almost concordance of knots in general 3-manifolds Y. Almost concordance is defined by considering knots in Y modulo concordance in Yx[0,1] and the action of the concordance group of knots in the 3-sphere that ties in local knots. We prove that the trivial fre…

AMP algorithms can be efficiently simulated by SDPs even with corrupted data.

Study improves posterior inference in neural processes with limited data.

We analyze dropout in deep networks with rectified linear units and the quadratic loss. Our results expose surprising differences between the behavior of dropout and more traditional regularizers like weight decay. For example, on some simple data sets dropout training produces negative weights even though the output i…

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

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

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

MAMBA learns policies competitive with multiple conflicting 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…

Machine learning models of music typically break up the task of composition into a chronological process, composing a piece of music in a single pass from beginning to end. On the contrary, human composers write music in a nonlinear fashion, scribbling motifs here and there, often revisiting choices previously made. In…

New oracle uses uncertainty for active classification with noisy feedback.

Quantum oracles help identify counterfactuals better than classical ones.

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

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 …

New oracles improve stochastic optimization with noisy or biased measurements.

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

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.

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

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

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.

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 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 …

Pairwise "same-cluster" queries are one of the most widely used forms of supervision in semi-supervised clustering. However, it is impractical to ask human oracles to answer every query correctly. In this paper, we study the influence of allowing "not-sure" answers from a weak oracle and propose an effective algorithm …

Study improves CTS's approximation regret for combinatorial bandits.

Improved Frank-Wolfe algorithm for constrained convex optimization with nearest extreme point oracle.

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

Riemannian Proximal Sampler improves sampling on manifold data.

New RLHF framework handles general preference oracles without reward functions.

Study on gradient complexity of private optimization with private oracles.

Study on costs of manipulating AMM-based price oracles.

CJE calibrates cheap LLM judges against an oracle, achieving high accuracy at a fraction of the cost.

Oracle inequality for sparse neural nets adapts to unknown structure.

We give nearly matching upper and lower bounds on the oracle complexity of finding $ε$-stationary points ($\| \nabla F(x) \| \leqε$) in stochastic convex optimization. We jointly analyze the oracle complexity in both the local stochastic oracle model and the global oracle (or, statistical learning) model. This allows u…

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

SoQal uses selective oracle questioning to improve active learning of cardiac signals.

RPI combines imitation and reinforcement learning to improve policies efficiently.

New algorithms adapt to friendly environments in online 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…

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