arXiv research

Efficiently approximates Sparse PCA with significant speedups and minor error.

Transformers excel at sparse token selection, surpassing FCNs in both worst and average cases.

Sparse curves on surfaces grow at a specific intermediate rate.

ACOWA improves distributed sparse classification with extra communication round.

New RL method MAC improves performance in sparse reward settings.

Improved Compressed Sensing by optimizing sparse solutions with mixed integer programming.

This paper develops several average-case reduction techniques to show new hardness results for three central high-dimensional statistics problems, implying a statistical-computational gap induced by robustness, a detection-recovery gap and a universality principle for these gaps. A main feature of our approach is to ma…

The Lasso performs well in ultra-sparse linear models with finite support size.

Dual averaging-type methods are widely used in industrial machine learning applications due to their ability to promoting solution structure (e.g., sparsity) efficiently. In this paper, we propose a novel accelerated dual-averaging primal-dual algorithm for minimizing a composite convex function. We also derive a stoch…

SLR tackles sparse linear regression problems, showing hardness for efficient algorithms.

We devise a one-shot approach to distributed sparse regression in the high-dimensional setting. The key idea is to average "debiased" or "desparsified" lasso estimators. We show the approach converges at the same rate as the lasso as long as the dataset is not split across too many machines. We also extend the approach…

BatchTopK SAEs improve GPT-2 and Gemma activations with adjustable sparsity.

In this article the package High-dimensional Metrics (\texttt{hdm}) is introduced. It is a collection of statistical methods for estimation and quantification of uncertainty in high-dimensional approximately sparse models. It focuses on providing confidence intervals and significance testing for (possibly many) low-dim…

Transformers show strengths and weaknesses in complexity analysis.

EASIER-net uses sparse networks to improve prediction accuracy for high-dimensional data.

Bayesian method identifies dynamical models with uncertainty quantification.

SAMS-VAE models cellular perturbations using sparse additive mechanisms.

The package High-dimensional Metrics (\Rpackage{hdm}) is an evolving collection of statistical methods for estimation and quantification of uncertainty in high-dimensional approximately sparse models. It focuses on providing confidence intervals and significance testing for (possibly many) low-dimensional subcomponents…

In the past decade, sparse principal component analysis has emerged as an archetypal problem for illustrating statistical-computational tradeoffs. This trend has largely been driven by a line of research aiming to characterize the average-case complexity of sparse PCA through reductions from the planted clique (PC) con…

New method for sparse kernel selection improves prediction accuracy.

We design a new sparse projection method for a set of vectors that guarantees a desired average sparsity level measured leveraging the popular Hoyer measure (an affine function of the ratio of the $\ell_1$ and $\ell_2$ norms). Existing approaches either project each vector individually or require the use of a regulariz…

Entropy regularization improves sparse model discovery in federated learning.

New insights link diverse statistical problems via secret leakage planted clique.

MAESTRO improves multimodal learning for dynamic time series with adaptive attention and robustness.

A fast method for Lasso and Logistic Lasso problems.

In this paper, we study the information-theoretic limits of community detection in the symmetric two-community stochastic block model, with intra-community and inter-community edge probabilities $\frac{a}{n}$ and $\frac{b}{n}$ respectively. We consider the sparse setting, in which $a$ and $b$ do not scale with $n$, and…

GrateTile optimizes CNN feature map storage for efficient data access.

A new method reduces communication costs in distributed learning.

Improved trajectory prediction for team sports using sparse outputs.

This paper investigates the average-case time complexity of certifying RIP matrices.

Improves test set performance and reduces out-of-sample disappointment for unstable models.

New research shows sparse topologies can lead to faster convergence in distributed optimization.

In the synthesis model signals are represented as a sparse combinations of atoms from a dictionary. Dictionary learning describes the acquisition process of the underlying dictionary for a given set of training samples. While ideally this would be achieved by optimizing the expectation of the factors over the underlyin…

Study on signal recovery from low-rank matrix with sparse noise.

Sparse oblique decision tree improves security rules for renewable power systems.

Reducing communication in training large-scale machine learning applications on distributed platform is still a big challenge. To address this issue, we propose a distributed hierarchical averaging stochastic gradient descent (Hier-AVG) algorithm with infrequent global reduction by introducing local reduction. As a gen…

We propose a regression algorithm that utilizes a learned dictionary optimized for sparse inference on a D-Wave quantum annealer. In this regression algorithm, we concatenate the independent and dependent variables as a combined vector, and encode the high-order correlations between them into a dictionary optimized for…

New algorithm minimizes regret in sparse reinforcement learning.

New algorithms find half-optimal independent sets in sparse graphs.

Excessive computational cost for learning large data and streaming data can be alleviated by using stochastic algorithms, such as stochastic gradient descent and its variants. Recent advances improve stochastic algorithms on convergence speed, adaptivity and structural awareness. However, distributional aspects of thes…

Kernel regression is a popular non-parametric fitting technique. It aims at learning a function which estimates the targets for test inputs as precise as possible. Generally, the function value for a test input is estimated by a weighted average of the surrounding training examples. The weights are typically computed b…

We propose a voted dual averaging method for online classification problems with explicit regularization. This method employs the update rule of the regularized dual averaging (RDA) method, but only on the subsequence of training examples where a classification error is made. We derive a bound on the number of mistakes…

Efficient solver for nonconvex tensor regularization reduces computational cost.

Large-scale regression problems where both the number of variables, $p$, and the number of observations, $n$, may be large and in the order of millions or more, are becoming increasingly more common. Typically the data are sparse: only a fraction of a percent of the entries in the design matrix are non-zero. Neverthele…

We consider a random sparse graph with bounded average degree, in which a subset of vertices has higher connectivity than the background. In particular, the average degree inside this subset of vertices is larger than outside (but still bounded). Given a realization of such graph, we aim at identifying the hidden subse…

Paper proposes a method to improve variational inference for sparse networks.

This paper establishes a statistical versus computational trade-off for solving a basic high-dimensional machine learning problem via a basic convex relaxation method. Specifically, we consider the {\em Sparse Principal Component Analysis} (Sparse PCA) problem, and the family of {\em Sum-of-Squares} (SoS, aka Lasserre/…

The inverse Potts problem to infer a Boltzmann distribution for homologous protein sequences from their single-site and pairwise amino acid frequencies recently attracts a great deal of attention in the studies of protein structure and evolution. We study regularization and learning methods and how to tune regularizati…