arXiv research

Paper explains why small-loss criterion works for learning from noisy labels.

This paper explains why distributional reinforcement learning is better than vanilla RL using small-loss bounds.

New bounds for bandits with graph feedback, improving previous results.

New method achieves small-loss regret bounds in random-order model.

Learning with noisy labels is one of the hottest problems in weakly-supervised learning. Based on memorization effects of deep neural networks, training on small-loss instances becomes very promising for handling noisy labels. This fosters the state-of-the-art approach "Co-teaching" that cross-trains two deep neural ne…

New algorithm achieves small-loss bounds in online learning with improved rates.

Bernard et al. (2015) study an optimal insurance design problem where an individual's preference is of the rank-dependent utility (RDU) type, and show that in general an optimal contract covers both large and small losses. However, their contracts suffer from a problem of moral hazard for paying more compensation for a…

New algorithms adapt to friendly environments in online learning.

INN method refines clean labeled data from noisy labels.

BCD algorithm finds global minima in neural networks.

Mirror descent with an entropic regularizer is known to achieve shifting regret bounds that are logarithmic in the dimension. This is done using either a carefully designed projection or by a weight sharing technique. Via a novel unified analysis, we show that these two approaches deliver essentially equivalent bounds …

We investigate online convex optimization in changing environments, and choose the adaptive regret as the performance measure. The goal is to achieve a small regret over every interval so that the comparator is allowed to change over time. Different from previous works that only utilize the convexity condition, this pa…

Since deep neural networks are over-parameterized, they can memorize noisy examples. We address such a memorization issue in the presence of label noise. From the fact that deep neural networks cannot generalize to neighborhoods of memorized features, we hypothesize that noisy examples do not consistently incur small l…

New bounds for online portfolio selection without smoothness assumptions.

Paper introduces a new $G^\star$ regret measure for online convex optimization with smooth losses.

Paper proposes a diagnostic tool for evaluating model performance out-of-sample.

This paper considers the design of optimal resource allocation policies in wireless communication systems which are generically modeled as a functional optimization problem with stochastic constraints. These optimization problems have the structure of a learning problem in which the statistical loss appears as a constr…

We present a filter correlation based model compression approach for deep convolutional neural networks. Our approach iteratively identifies pairs of filters with the largest pairwise correlations and drops one of the filters from each such pair. However, instead of discarding one of the filters from each such pair naï…

Paper proposes a federated learning framework for relative fairness.

Study disproves a generalized numerical criterion for certain pairs.

New polynomial criterion for periodic knots identified.

New algorithms optimize a soft-robust criterion in reinforcement learning, reducing conservatism.

Data aggregation improves HAC for resource-constrained systems.

We introduce a new criterion to determine the order of an autoregressive model fitted to time series data. It has the benefits of the two well-known model selection techniques, the Akaike information criterion and the Bayesian information criterion. When the data is generated from a finite order autoregression, the Bay…

How can we control for latent discrimination in predictive models? How can we provably remove it? Such questions are at the heart of algorithmic fairness and its impacts on society. In this paper, we define a new operational fairness criteria, inspired by the well-understood notion of omitted variable-bias in statistic…

We propose a general framework for studying adaptive regret bounds in the online learning framework, including model selection bounds and data-dependent bounds. Given a data- or model-dependent bound we ask, "Does there exist some algorithm achieving this bound?" We show that modifications to recently introduced sequen…

Modified Bakry-Émery criterion inequality for Tsallis entropy monotonicity.

Given a similarity graph between items, correlation clustering (CC) groups similar items together and dissimilar ones apart. One of the most popular CC algorithms is KwikCluster: an algorithm that serially clusters neighborhoods of vertices, and obtains a 3-approximation ratio. Unfortunately, KwikCluster in practice re…

A widely applicable Bayesian information criterion (Watanabe, 2013) is applicable for both regular and singular models in the model selection problem. This criterion tends to overestimate the log marginal likelihood. We identify an overestimating term of a widely applicable Bayesian information criterion. Adjustment of…

New criterion improves predictive evaluation in weighted inference scenarios.

Criterion for stopping conjugacy class enumeration in triangle groups.

In [D.A. Fedoseev, V.O. Manturov, A sliceness criterion for odd free knots,arXiv:1707.04923], the authors proved a sliceness criterion for odd free knots: free knots with odd chords. In the present paper we give a similar criterion for stably odd free knots. Some additional results on knot sliceness and cobordism are g…

As deep neural network (NN) methods have matured, there has been increasing interest in deploying NN solutions to "edge computing" platforms such as mobile phones or embedded controllers. These platforms are often resource-constrained, especially in energy storage and power, but state-of-the-art NN architectures are de…

New criterion for solving inverse Hessian equations, including J-equation.

Criterion for nilpotent Lie groups to have nilsolitons.

Study proposes a stopping criterion for active learning based on error stability.

Paper defends sensitive attributes in GNNs from inference attacks.

Clarifies boundary criterion for non-one-ended subgroups in cubulation theory.

This paper tackles fairness in PCA by balancing it with reconstruction error.

We investigate how price variations of a stock are transformed into profits and losses (P&Ls) of a trend following strategy. In the frame of a Gaussian model, we derive the probability distribution of P&Ls and analyze its moments (mean, variance, skewness and kurtosis) and asymptotic behavior (quantiles). We show that …

Extends Kelly Criterion to more complex betting scenarios.

Derives criteria for Kähler structures on holomorphic submersions.

Partial answer to affineness of entire Grauert tubes, with Stein manifold criterion.

Optimizes recommendation models using skew normal distribution.

Criterion for solvability of complex 2-Hessian equation on compact Kähler manifolds.

New criterion assesses cluster separability for validation.

Criterion found for Teichmüller extremal maps on infinite Riemann surfaces.

This paper proves a Nakai-Moishezon criterion for complex Hessian equations.