Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

3877115153 · Jun 202019922001200920172026
48 results for matrix Catoni

GL-LowPopArt improves minimax-optimal estimation for trace regression.

problem Minimizing estimation error in generalized low-rank trace regression.
method Two-stage approach: nuclear norm regularization followed by matrix Catoni estimation.
result Achieves instance-wise optimal error bounds up to condition number.

Paper tackles heavy-tailed data without finite variance, proposing robust risk minimization.

problem Empirical risk minimization under heavy-tailed data with finite pp-th moment.
method Minimizes risk values robustly estimated via Catoni's method, using generalized generic chaining.
result Shows better performance of optimizer based on empirical risks via Catoni-style estimation.

The paper extends confidence sequences for infinite variance data.

problem Addressing confidence sequences for distributions with infinite variance.
method Establishing lower bounds and deriving tight confidence sequences for relaxed bounded pthp^{th}-moment distributions.
result Derived confidence sequences are tighter than those using Dubins-Savage inequality.

This paper achieves first-order regret bounds in reinforcement learning with large state spaces.

problem Achieving first-order regret bounds in reinforcement learning with large state spaces.
method Developed a novel robust self-normalized concentration bound based on the robust Catoni mean estimator.
result Obtained regret bounds scaling as O~(d3H3V1K+d3.5H3logK)\widetilde{\mathcal{O}}(\sqrt{d^3 H^3 \cdot V_1^\star \cdot K} + d^{3.5}H^3\log K ).

The paper develops a robust algorithm for contextual bandits with heavy-tailed rewards.

problem Contextual bandits with heavy-tailed rewards.
method Develops an algorithm based on Catoni's estimator for robust statistics, applying it to contextual bandits with general function approximation.
result Establishes regret bounds that depend on cumulative reward variance and logarithmically on the reward range and number of rounds.

The aim of this paper is to generalize the PAC-Bayesian theorems proved by Catoni in the classification setting to more general problems of statistical inference. We show how to control the deviations of the risk of randomized estimators. A particular attention is paid to randomized estimators drawn in a small neighbor…

2007-12-11abs ↗pdf ↗

The stochastic multi-armed bandit problem is well understood when the reward distributions are sub-Gaussian. In this paper we examine the bandit problem under the weaker assumption that the distributions have moments of order 1+ε, for some ε(0,1]ε\in (0,1]. Surprisingly, moments of order 2 (i.e., finite variance) are suffi…

2012-09-08abs ↗pdf ↗

We develop time-uniform confidence spheres for estimating means of random vectors.

problem Sequential mean estimation in high-dimensional spaces.
method Derive time-uniform confidence sphere sequences (CSSs) for various types of random vectors.
result Optimal CSSs for log-concave, sub-Gaussian, and sub-ψψ random vectors.

Paper improves PAC-Bayes bounds for various loss types.

problem Improving PAC-Bayes bounds for different types of losses.
method Introducing new high-probability PAC-Bayes bounds for bounded and general tail behaviors losses, and extending to anytime-valid bounds.
result New fast-rate and mixed-rate bounds for losses with bounded ranges, and parameter-free bounds for losses with general tail behaviors.

Improved Clipped-SGD achieves near-optimal heavy-tailed statistical estimation in streaming settings.

problem High-dimensional heavy-tailed statistical estimation in streaming with memory constraints.
method Stochastic convex optimization with Clipped-SGD, proving near-optimal sub-Gaussian statistical rates.
result Clipped-SGD achieves an error of Tr(Σ)+Tr(Σ)Σ2log(log(T)δ)T\sqrt{\frac{\mathsf{Tr}(Σ)+\sqrt{\mathsf{Tr}(Σ)\|Σ\|_2}\log(\frac{\log(T)}δ)}{T}} with probability 1δ1-δ.

We initiate the study of learning in contextual bandits with the help of loss predictors. The main question we address is whether one can improve over the minimax regret O(T)\mathcal{O}(\sqrt{T}) for learning over TT rounds, when the total error of the predictor ET\mathcal{E} \leq T is relatively small. We provide a com…

2020-03-04abs ↗pdf ↗

New information-theoretic bounds improve machine learning generalization.

problem Improving machine learning generalization beyond traditional complexity-based methods.
method Introducing bounds using Wasserstein distance and structured methods to incorporate geometry and individual data dependence.
result Established connections between different bounds and introduced new tighter bounds for various loss functions.

New matrix reveals cluster info in sparse directed graphs.

problem Analyzing cluster information in directed graphs.
method Proposed complex non-backtracking matrix integrating Hermitian adjacency matrix and non-backtracking matrix properties.
result The complex non-backtracking matrix holds cluster information, especially for sparse directed graphs.

Generalised matrix-matrix multiplication forms the kernel of many mathematical algorithms. A faster matrix-matrix multiply immediately benefits these algorithms. In this paper we implement efficient matrix multiplication for large matrices using the floating point Intel Pentium SIMD (Single Instruction Multiple Data) a…

2019-11-18abs ↗pdf ↗

Classifies SL(n) covariant matrix-valued valuations on Lp-spaces.

problem Classifying SL(n) covariant matrix-valued valuations on Lp-spaces.
method Established a complete classification for continuous and SL(n) covariant matrix-valued valuations on Lp(Rn,|x|2dx), eliminating matrix symmetry assumption.
result Unique characterization of such valuations by the moment matrix in n>2, rotation matrix in 2D.

Unified approach for robust low rank matrix estimation with adversaries.

problem Robust low rank matrix estimation in the presence of adversaries.
method Unified approach combining Huber loss and nuclear norm penalization.
result Sharp estimation error bounds for matrix compressed sensing and completion.

Most recent results in matrix completion assume that the matrix under consideration is low-rank or that the columns are in a union of low-rank subspaces. In real-world settings, however, the linear structure underlying these models is distorted by a (typically unknown) nonlinear transformation. This paper addresses the…

2015-12-29abs ↗pdf ↗

Recommender systems are widely used to recommend the most appealing items to users. These recommendations can be generated by applying collaborative filtering methods. The low-rank matrix completion method is the state-of-the-art collaborative filtering method. In this work, we show that the skewed distribution of rati…

2019-04-22abs ↗pdf ↗

New method improves robust low-rank matrix completion for computer vision.

problem Robust low-rank matrix completion for partially observed data.
method Formulated as a nonsmooth Riemannian optimization problem over Grassmann manifold, solved with an alternating manifold proximal gradient continuation method.
result Demonstrated advantages over existing approaches in background extraction from surveillance videos.

Matrix completion is a modern missing data problem where both the missing structure and the underlying parameter are high dimensional. Although missing structure is a key component to any missing data problems, existing matrix completion methods often assume a simple uniform missing mechanism. In this work, we study ma…

2018-12-19abs ↗pdf ↗

Matrix approximation is a common tool in machine learning for building accurate prediction models for recommendation systems, text mining, and computer vision. A prevalent assumption in constructing matrix approximations is that the partially observed matrix is of low-rank. We propose a new matrix approximation model w…

2013-01-15abs ↗pdf ↗

Unified framework for nonconvex matrix completion with linearly parameterized factors.

problem Matrix completion with improved accuracy using linearly parameterized factors.
method Unified nonconvex optimization framework with Correlated Parametric Factorization condition.
result Uniform upper bounds for low-rank estimation at any local minimum.

Matrix completion is a problem that arises in many data-analysis settings where the input consists of a partially-observed matrix (e.g., recommender systems, traffic matrix analysis etc.). Classical approaches to matrix completion assume that the input partially-observed matrix is low rank. The success of these methods…

2017-04-30abs ↗pdf ↗

3-manifold triangulation can be reconstructed from its intersection matrix.

problem Reconstructing the triangulation of 3-manifolds from their intersection matrix.
method Using the intersection matrix of a simplicial complex to determine the triangulation of a 3-manifold up to isomorphism.
result The intersection matrix is sufficient to determine the triangulation of a 3-manifold up to isomorphism.

We give the first algorithm for Matrix Completion whose running time and sample complexity is polynomial in the rank of the unknown target matrix, linear in the dimension of the matrix, and logarithmic in the condition number of the matrix. To the best of our knowledge, all previous algorithms either incurred a quadrat…

2014-07-15abs ↗pdf ↗

Paper presents a new framework for covariance matrix estimation with geometric insights.

problem Challenges in covariance matrix estimation, especially in finding suitable models and efficient estimation methods.
method General framework for linear restrictions on different transformations of the covariance matrix, including matrix logarithm and its inverse.
result Yields an MM-estimator with MM-estimation allowing for straightforward asymptotic and finite sample analysis.

Study improves fractional posterior for 1-bit matrix completion.

problem Estimating a binary matrix from observed entries.
method Fractional posterior approach with low-rank factorization and spectral scaled Student priors.
result Concentration results for fractional posterior, demonstrating effectiveness in matrix recovery.

In this paper, we propose an online algorithm to compute matrix factorizations. Proposed algorithm updates the dictionary matrix and associated coefficients using a single observation at each time. The algorithm performs low-rank updates to dictionary matrix. We derive the algorithm by defining a simple objective funct…

2015-06-14abs ↗pdf ↗

Incorporates matrix exponential into generative flows for improved performance.

problem Improving generative flow models for better density estimation.
method Integrates matrix exponential into generative flows, proposing new layers and modifying network architecture.
result The proposed model achieves great performance on density estimation.

Consider a movie recommendation system where apart from the ratings information, side information such as user's age or movie's genre is also available. Unlike standard matrix completion, in this setting one should be able to predict inductively on new users/movies. In this paper, we study the problem of inductive matr…

2013-06-04abs ↗pdf ↗

Matrix SMD converges to unique solution minimizing Bregman divergence.

problem High-dimensional multi-output classification and matrix completion problems.
method Stochastic Mirror Descent with matrix parameters and matrix mirror functions.
result Matrix SMD converges exponentially to the unique solution minimizing Bregman divergence.

Paper derives matrix formulae and proves skein relations for non-orientable surfaces in quasi-cluster algebras.

problem Understanding quasi-cluster algebras on non-orientable surfaces.
method Developed matrix formulae and proved skein relations for quasi-cluster variables.
result Laurent expansion and skein relations for quasi-cluster variables on non-orientable surfaces.

Gradient descent proves global convergence for 4-layer matrix factorization.

problem Global convergence of gradient descent on four-layer matrix factorization under random initialization.
method New techniques to show saddle-avoidance properties and extend eigenvalue theories.
result Polynomial-time global convergence guarantee for randomly initialized gradient descent on four-layer matrix factorization.