Efficiently reduces tensor ranks using mean-field approximation.
problem Low-rank approximation of non-negative tensors.
method Mean-field approximation of tensor rank reduction.
result Our algorithm achieves faster and competitive tensor rank reduction.
In this paper, we propose a low-rank approximation method based on discrete least-squares for the approximation of a multivariate function from random, noisy-free observations. Sparsity inducing regularization techniques are used within classical algorithms for low-rank approximation in order to exploit the possible sp…
Paper proposes a new technique to compress CNNs while maintaining accuracy.
problem CNNs struggle with traditional low-rank approximation methods, leading to degraded accuracy.
method Introduces a training technique that finds a flat minimum in low-rank approximation without a decomposed structure.
result CNN models can be compressed with higher accuracy and lower computation than conventional methods.
Paper tackles fair low-rank approximation and column subset selection.
problem Minimize loss over sub-populations in machine learning.
method Developed algorithms for fair low-rank approximation and fair column subset selection.
result Achieved polynomial time algorithms for fair low-rank approximation.
New algorithms minimize non-zero entries in low-rank approximations.
problem Minimizing non-zero entries in low-rank approximations of matrices.
method Approximation algorithms for minimizing ℓ0-norm of rank-k matrices. result First provable guarantees for ℓ0-Low Rank Approximation for k>1. An algorithm finds approximate rankings from pairwise comparisons with near-optimal comparisons.
problem Ranking items based on pairwise comparisons with minimal comparisons.
method Active ranking algorithm that decides comparisons based on confidence intervals.
result The algorithm succeeds in recovering approximate rankings with near-optimal comparisons.
We develop an efficient algorithm for low-rank approximation with improved approximation guarantees.
problem Optimal low-rank approximation of matrices with ℓ1 norm constraints. method Polynomial time column subset selection-based algorithm achieving ildeO(k1/2)-approximation. result Improved approximation guarantees for ℓ1 low-rank approximation. New methods recover best rank-r approximations from few entries.
problem Recovering best rank-r approximations from limited data entries.
method Two agnostic approaches: spectral truncation and projected gradient descent.
result Projected gradient descent yields superior performance.
Improved Top-N recommendations with novel rank approximation.
problem Low accuracy in recommender systems.
method Linear sparse and low-rank representation with nuclear norm relaxation.
result Significantly improved Top-N recommendation accuracy.
Greedy method improves low rank matrix estimation with new approximation guarantees.
problem Low rank matrix estimation under restricted strong convexity and smoothness.
method Novel greedy algorithm analysis linking to combinatorial optimization.
result Improved approximation guarantees and statistical recovery.
Paper solves low-rank Boolean matrix approximation using integer programming.
problem Finding low-rank approximations to Boolean matrices.
method Integer programming formulation with polynomial variables and constraints.
result First computationally tractable integer programming approach.
The paper introduces algorithms for efficient low-rank matrix approximation.
problem Efficiently approximating large matrices while preserving their properties.
method Random linear images (sketches) of the matrix, with error bounds for quality control.
result Simple, accurate, numerically stable methods for low-rank approximation.
We accelerate the power method for strong low-rank approximation using fast sketching.
problem Efficiency bottleneck in power method for large target ranks.
method Developed an algorithmic and theoretical framework for accelerating the power method using fast sketching.
result Simple and provably efficient methods for singular value decomposition, low-rank factorization, and Nyström approximation.
New algorithm for weighted low rank approximation with provable guarantees.
problem Weighted low rank approximation (WLRA) is computationally hard.
method Reweights the low rank solution using the weight matrix itself.
result Provably optimal approximation guarantees for WLRA.
The study assesses low-rank approximations in Gaussian Process regression.
problem Improving Gaussian Process regression efficiency with low-rank approximations.
method Analyzes two low-rank approximations: random Fourier features and Mercer expansion truncation.
result Bounds on the divergence and error between exact and approximate GP models.
The study assesses low-rank approximations in Gaussian Process regression.
problem Improving the efficiency of Gaussian Process regression while maintaining accuracy.
method Analyzes two low-rank approximations: random Fourier features and Mercer expansion truncation, and bounds the divergence and error between exact and approximate models.
result Theoretical bounds on the divergence and error between exact and approximate Gaussian Process models are provided.
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…
Low-rank matrices explain data science patterns.
problem Why do data matrices often have low rank?
method A generative model with latent variables and piecewise functions.
result Approximating large matrices with low rank is feasible.
New algorithm approximates large psd matrices from sketches.
problem Large-scale positive-semidefinite matrices from streaming data.
method Combines Nystrom approximation with rank truncation.
result Achieves prescribed relative error in Schatten 1-norm.
Polynomial sketch approximates functions of low-rank matrices efficiently.
problem Approximating element-wise functions of low-rank matrices without full access.
method Combining polynomial approximation and tensor sketch for monomials.
result Efficient algorithm with lower complexity than full matrix access.
New method for initializing low-rank neural networks improves performance.
problem Training low-rank neural networks efficiently and accurately.
method Inspired by function approximation, proposes a novel low-rank initialization framework.
result Demonstrates significant gap between spectral and low-rank initialization approaches.
Paper proposes a new convex relaxation for low-rank approximation problems.
problem Finding low-rank approximations with convex constraints in data analysis.
method Proposes a new convex relaxation using the convex envelope of the squared Frobenius norm and rank constraint.
result Solutions to the convex relaxation coincide with the original non-convex problem under certain conditions.
Algorithm learns a better sketch matrix for low-rank approximations.
problem Efficiently compute low-rank approximations of large matrices.
method Uses a learned sketch matrix instead of random matrix for optimization.
result Learned sketch matrix reduces approximation loss significantly compared to random matrix.
Researchers discover phase transitions in estimating object ranks from pairwise interactions.
problem Estimating the underlying ranks of objects from pairwise comparisons or collaborations.
method Characterized optimal statistical error rates for various signal-to-noise ratios.
result Phase transitions between optimal error rates of polynomial, exponential, zero, and trivial.
Solves low-rank approximation problems in Hilbert spaces.
problem Low-rank approximation in Hilbert spaces.
method Closed-form solutions and error bounds for bounded linear operators.
result Generalization to bounded linear operators from finite dimensions.
Matrix rank minimization problem is in general NP-hard. The nuclear norm is used to substitute the rank function in many recent studies. Nevertheless, the nuclear norm approximation adds all singular values together and the approximation error may depend heavily on the magnitudes of singular values. This might restrict…
Numerous applications in data mining and machine learning require recovering a matrix of minimal rank. Robust principal component analysis (RPCA) is a general framework for handling this kind of problems. Nuclear norm based convex surrogate of the rank function in RPCA is widely investigated. Under certain assumptions,…
Study nonconvex matrix completion for low-rank approximation without rank assumptions.
problem Low-rank approximation of positive semidefinite matrices from partial entries.
method Nonconvex optimization, local-minimum analysis, no spurious local minima.
result Improved sampling rate for nonconvex matrix completion with no spurious local minima.
Paper develops fast low-rank approximation for smoothing splines.
problem Computational infeasibility of fitting cubic smoothing splines to large datasets.
method Low-rank approximation using eigensystem truncation.
result The method provides accurate, fast estimates with error bounds.
New method reduces computational cost for nonnegative low rank matrix approximation.
problem Efficiently compute nonnegative low rank matrix approximation for nonnegative matrices.
method Alternating projections onto tangent spaces of fixed rank matrices manifold and nonnegative matrix manifold.
result Sequence converges linearly to optimal solutions, showing better performance in terms of computational time and accuracy.
This paper tackles poor approximations in learning-to-rank algorithms and proposes exact reranking methods.
problem Poor approximations in learning-to-rank algorithms based on convex proxies.
method Exact reranking algorithms based on mathematical programming.
result A relaxed version of the exact problem has the same optimal solution.
Simple algorithms improve ℓp-norm low-rank approximations.
problem Efficiently approximating matrices with low rank using ℓp norms. method Non-convex gradient-based algorithms with polynomial time complexity.
result Achieves (1+ε)-OPT approximations. We simplify SSL by approximating redundant structural components with low-rank factorization.
problem Improving self-supervised learning performance with limited labeled data.
method Low-rank approximation of structural redundancy, introducing ε_s to measure approximation quality.
result The proposed method enhances SSL performance, as shown by theoretical and experimental validations.
Stochastic gradient descent on manifolds improves low-rank approximation.
problem Efficiently approximate large matrices with lower rank.
method Stochastic gradient descent on a manifold.
result Algorithm outperforms Euclidean space methods on Netflix Prize data.
Matrix rank minimizing subject to affine constraints arises in many application areas, ranging from signal processing to machine learning. Nuclear norm is a convex relaxation for this problem which can recover the rank exactly under some restricted and theoretically interesting conditions. However, for many real-world …
WMRB improves ranking accuracy and efficiency in scalable batch training.
problem Improving ranking accuracy and efficiency in large-scale recommendation systems.
method WMRB uses a new rank estimator and an efficient batch training algorithm.
result WMRB consistently outperforms WARP and other baselines in three item recommendation tasks.
Paper bounds the minimal rank for kernel ridge regression approximations.
problem Efficient memory and computation for kernel ridge regression.
method Lower bound on minimal rank for reliable prediction power.
result Nyström method's computational cost is almost linear in sample size.
Unified error analysis for low-rank approximation improves data assimilation performance.
problem Analyzing the error in low-rank approximation methods for data assimilation.
method Unified stochastic analysis framework for Frobenius norm error bounds on centered and non-standard Gaussian matrices.
result Unified bounds provide clearer interpretations and enable better practical choices for covariance matrices.
Paper improves tensor approximation for streaming data.
problem Challenges in finding accurate low-tubal-rank tensor approximations in streaming settings.
method Extends Frequent Directions for efficient low-tubal-rank tensor approximation.
result The new algorithm achieves arbitrarily small approximation error with linear sketch size growth.
Improved Nystrom method reduces landmark points for better kernel matrix approximations.
problem Poor performance and lack of theoretical guarantees in standard Nystrom method.
method QR decomposition for efficient rank reduction in fixed-rank Nystrom approximations.
result Improved accuracy in many cases with nearly identical computational complexity.
A modified SPA preconditioner enhances noise robustness in separable NMFs.
problem Noisy separable NMFs are challenging to solve efficiently.
method Proposes a modified SPA preconditioner to enhance noise robustness.
result The modified SPA preconditioner improves noise robustness without significantly increasing computational cost.
Paper develops a new weighted low-rank matrix approximation technique.
problem Matrix completion with missing data.
method Element-wise weighted generalization of low-rank matrix approximation.
result Proposes an algorithm and acceleration techniques for solving the weighted problem.
Truncated Singular Value Decomposition (SVD) calculates the closest rank-k approximation of a given input matrix. Selecting the appropriate rank k defines a critical model order choice in most applications of SVD. To obtain a principled cut-off criterion for the spectrum, we convert the underlying optimization prob…
Paper presents a rank-1 approximation method for natural policy gradients in deep RL.
problem Computing natural gradients requires inverting the Fisher Information Matrix, which is computationally expensive.
method Develops a rank-1 approximation to the inverse Fisher Information Matrix for efficient natural policy optimization.
result The rank-1 approximation converges faster and has similar sample complexity to stochastic policy gradient methods.
Novel algorithm for Markov decision processes using rank-one approximation.
problem Solving planning and learning problems of Markov decision processes.
method Policy iteration with rank-one approximation of transition probability matrix.
result The proposed algorithm consistently outperforms first-order algorithms and their accelerated versions.
A simple likelihood approximation works well for large number of classes.
problem Training probabilistic classifiers with a large number of classes.
method Directly approximates the likelihood and relates to a ranking objective.
result Simple approach works well on toy problems and is competitive.
Solves rank-dependent mean field game with common noise.
problem Rank-dependent rewards in competitive game settings.
method Mean field game approach with common noise.
result Approximate Nash equilibrium and convergence rate.
Improved Frank-Wolfe method tackles nonsmooth functions.
problem Efficiently solving large nonsmooth problems with sparse structures.
method Optimizes for approximation quality over all affine approximations.
result Overcomes issues with existing nonsmooth methods in low-rank matrix estimation.