arXiv research

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

TCT improves federated learning by convexifying neural networks.

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

DCCNNs reduce computational overhead and ambiguity in convolutional neural networks.

DNCF framework recovers real scenes from imperfect images robustly.

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 …

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…

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…

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.

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…

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…

We give examples of symplectic actions of a cyclic group, inducing a trivial action on homology, on four-manifolds that admit Hamiltonian circle actions, and show that they do not extend to Hamiltonian circle actions. Our work applies holomorphic methods to extend combinatorial tools developed for circle actions to stu…

Reduces proper actions to simpler core actions for analysis.

Introduces Conditional Action Trees to simplify RL action spaces.

One problem in the application of reinforcement learning to real-world problems is the curse of dimensionality on the action space. Macro actions, a sequence of primitive actions, have been studied to diminish the dimensionality of the action space with regard to the time axis. However, previous studies relied on human…

Study polar actions on Damek-Ricci spaces, proving existence and finding examples.

New RL algorithm tackles complex discrete action spaces.

Reduction principles for proper actions on smooth manifolds.

Totally geodesic sections found in polar actions.

Simplifies large action space bandits by selecting representative actions.

We study isometric actions on Riemannian symmetric spaces of noncompact type which are induced by reductive algebraic subgroups of the isometry group. We show that for such an action there exists a corresponding isometric action on a dual compact symmetric space, which reflects many properties of the original action. F…

Classifies totally geodesic submanifolds and polar actions on Stiefel manifolds.

Conditions for reducing quasi-actions to tree actions and group properties.

The study proves conditions for symplectic torus actions on manifolds with non-contractible orbits.

We identify action representations from video data, proving their statistical benefits.

Study properties of orbits of Hermann actions without commutability assumptions.

We classify the polar actions on the complex hyperbolic plane up to orbit equivalence. Apart from the trivial and transitive polar actions, there are five polar actions of cohomogeneity one and four polar actions of cohomogeneity two.

A new method learns action representations for reinforcement learning.

The paper studies curvatures and austere properties of orbits in symmetric spaces.

New reinforcement learning framework for adapting to new actions.

AQL uses amortized inference to handle high-dimensional action spaces in Q-learning.

Defines and computes a generalized spectral action for Lorentz warped products.

The paper studies acylindrical actions on trees and proves acylindrical hyperbolicity of Baumslag-Solitar groups.

The study examines largest hyperbolic actions in groups and finds many do not exist.

UTE improves reinforcement learning by measuring action uncertainty, enhancing policy learning efficiency.

Classifies polar actions on 3D homogeneous spaces.

Proper actions on bornological spaces are characterized with compatible coarse structures.