arXiv research

This research improves PAC-Bayesian bounds for classification tasks using convexified loss.

The use of convex regularizers allows for easy optimization, though they often produce biased estimation and inferior prediction performance. Recently, nonconvex regularizers have attracted a lot of attention and outperformed convex ones. However, the resultant optimization problem is much harder. In this paper, for a …

TCT improves federated learning by convexifying neural networks.

We formalize and study the natural approach of designing convex surrogate loss functions via embeddings, for problems such as classification, ranking, or structured prediction. In this approach, one embeds each of the finitely many predictions (e.g.\ rankings) as a point in $\mathbb{R}^d$, assigns the original loss val…

DCCNNs reduce computational overhead and ambiguity in convolutional neural networks.

This paper extends combinatorial semi-bandits to graph feedback, improving regret bounds.

In classification models fairness can be ensured by solving a constrained optimization problem. We focus on fairness constraints like Disparate Impact, Demographic Parity, and Equalized Odds, which are non-decomposable and non-convex. Researchers define convex surrogates of the constraints and then apply convex optimiz…

DNCF framework recovers real scenes from imperfect images robustly.

New algorithm improves dataset distillation with 108% improvement on ImageNet.

The stochastic block model (SBM) is a popular framework for studying community detection in networks. This model is limited by the assumption that all nodes in the same community are statistically equivalent and have equal expected degrees. The degree-corrected stochastic block model (DCSBM) is a natural extension of S…

In this paper we prove necessary and sufficient conditions for the Kobayashi metric on a convex domain to be Gromov hyperbolic. In particular we show that for convex domains with $C^\infty$ boundary being of finite type in the sense of D'Angelo is equivalent to the Gromov hyperbolicity of the Kobayashi metric. We also …

New method accelerates convergence for entropy-regularized reinforcement learning problems.

This study uses neural networks to solve interpolation problems with sparse, infinitely wide layers.

The omnipresence of deep learning architectures such as deep convolutional neural networks (CNN)s is fueled by the synergistic combination of ever-increasing labeled datasets and specialized hardware. Despite the indisputable success, the reliance on huge amounts of labeled data and specialized hardware can be a limiti…

The problem of low-rank approximation with convex constraints, which appears in data analysis, system identification, model order reduction, low-order controller design and low-complexity modelling is considered. Given a matrix, the objective is to find a low-rank approximation that meets rank and convex constraints, w…

Optimization problems with rank constraints appear in many diverse fields such as control, machine learning and image analysis. Since the rank constraint is non-convex, these problems are often approximately solved via convex relaxations. Nuclear norm regularization is the prevailing convexifying technique for dealing …

The paper analyzes PPM for nonconvex-nonconcave problems, identifying three regions with varying convergence guarantees.

Researchers improve transformer networks' optimization and understanding.

Low-rank inducing unitarily invariant norms have been introduced to convexify problems with low-rank/sparsity constraint. They are the convex envelope of a unitary invariant norm and the indicator function of an upper bounding rank constraint. The most well-known member of this family is the so-called nuclear norm. To …

Graph clustering involves the task of dividing nodes into clusters, so that the edge density is higher within clusters as opposed to across clusters. A natural, classic and popular statistical setting for evaluating solutions to this problem is the stochastic block model, also referred to as the planted partition model…

A new framework for sparse regression models with slow variations.

We consider two closely related problems: planted clustering and submatrix localization. The planted clustering problem assumes that a random graph is generated based on some underlying clusters of the nodes; the task is to recover these clusters given the graph. The submatrix localization problem concerns locating hid…

Introduces Fitzpatrick losses, tighter than Fenchel-Young losses.

We study losses for binary classification and class probability estimation and extend the understanding of them from margin losses to general composite losses which are the composition of a proper loss with a link function. We characterise when margin losses can be proper composite losses, explicitly show how to determ…

We present the Tamed Cross Entropy (TCE) loss function, a robust derivative of the standard Cross Entropy (CE) loss used in deep learning for classification tasks. However, unlike other robust losses, the TCE loss is designed to exhibit the same training properties than the CE loss in noiseless scenarios. Therefore, th…

Unified surrogate loss framework for multi-label learning with strong consistency guarantees.

This paper introduces new loss functions for balanced multi-class classification.

We present $α$-loss, $α\in [1,\infty]$, a tunable loss function for binary classification that bridges log-loss ($α=1$) and $0$-$1$ loss ($α= \infty$). We prove that $α$-loss has an equivalent margin-based form and is classification-calibrated, two desirable properties for a good surrogate loss function for the ideal y…

This work broadens calibeating to various proper losses using Bregman divergence.

This work generalizes calibeating for a broader range of proper losses using Bregman divergence.

Proposes squentropy loss for improved classification accuracy and model calibration.

New loss function calibrates WW-hinge loss for multiclass SVM.

The study analyzes a model for aggregate losses with dependent and overdispersed inter-losses times.

Symmetric losses improve classifier robustness from corrupted labels.

Two new algorithms improve performance in adversarial bandits with unbounded losses.

Paper explores connections between loss functions and consistency in binary classification and regression.

Paper introduces a new topological loss for better convergence.

Novel loss functions improve decision tree learning from noisy data.

Theoretical analysis of cross-entropy loss functions and their robustness.

This paper improves operational risk modeling by selecting better loss severity distributions.

This paper improves loss functions for deep learning with noisy labels.

Classification is the most important process in data analysis. However, due to the inherent non-convex and non-smooth structure of the zero-one loss function of the classification model, various convex surrogate loss functions such as hinge loss, squared hinge loss, logistic loss, and exponential loss are introduced. T…

We study cross-country GDP losses due to financial crises in terms of frequency (number of loss events per period) and severity (loss per occurrence). We perform the Loss Distribution Approach (LDA) to estimate a multi-country aggregate GDP loss probability density function and the percentiles associated to extreme eve…

The paper proves deep learning can be robust with certain loss functions.

The paper explores transferability of adversarial examples between convex and 01 loss models, finding non-transferability due to different decision boundaries caused by outliers.

Symmetrizes loss functions to improve neural network robustness against noisy labels.

EnsLoss combines multiple loss functions to prevent overfitting in classification.

Quantification of the stationary points and the associated basins of attraction of neural network loss surfaces is an important step towards a better understanding of neural network loss surfaces at large. This work proposes a novel method to visualise basins of attraction together with the associated stationary points…