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.
Stochastic approximation algorithms show exponential progress bounds.
New bounds derived for KG algorithm's performance in finite time.
This paper compares Grid Search, Random Search, and Genetic Algorithm for NAS.
Unified framework for combinatorial and rounding algorithms in experimental design.
One-shot algorithm for feature-distributed kernel PCA reduces communication costs.
No algorithm outperforms uniform sampling in A/B testing.
Adaptive algorithm improves convergence rate of Langevin dynamics.
A fast sketching algorithm solves regularized least squares problems efficiently.
Paper improves convergence rates and step sizes for gradient algorithms.
Approximate algorithms for structured prediction problems---such as LP relaxations and the popular alpha-expansion algorithm (Boykov et al. 2001)---typically far exceed their theoretical performance guarantees on real-world instances. These algorithms often find solutions that are very close to optimal. The goal of thi…
Study limits of testing algorithms without assumptions, finding key performance bounds.
Algorithm improves vanilla option pricing accuracy during and before COVID-19.
The exchange algorithm is studied for its convergence and asymptotic variance.
We investigate regularized algorithms combining with projection for least-squares regression problem over a Hilbert space, covering nonparametric regression over a reproducing kernel Hilbert space. We prove convergence results with respect to variants of norms, under a capacity assumption on the hypothesis space and a …
Develops an actor-critic algorithm for risk-sensitive Markov decision processes.
New algorithm ensures consistent results in constrained MAB problems.
Theoretical analysis confirms non-conservative algorithms can converge to optimal policies.
We propose accelerated randomized coordinate descent algorithms for stochastic optimization and online learning. Our algorithms have significantly less per-iteration complexity than the known accelerated gradient algorithms. The proposed algorithms for online learning have better regret performance than the known rando…
One popular method for dealing with large-scale data sets is sampling. For example, by using the empirical statistical leverage scores as an importance sampling distribution, the method of algorithmic leveraging samples and rescales rows/columns of data matrices to reduce the data size before performing computations on…
In this paper, we firstly give a brief introduction of expectation maximization (EM) algorithm, and then discuss the initial value sensitivity of expectation maximization algorithm. Subsequently, we give a short proof of EM's convergence. Then, we implement experiments with the expectation maximization algorithm (We im…
We propose a novel probabilistic method for detection of objects in noisy images. The method uses results from percolation and random graph theories. We present an algorithm that allows to detect objects of unknown shapes in the presence of random noise. The algorithm has linear complexity and exponential accuracy and …
Introduces LDM to estimate machine learning algorithm capacity.
Simplifies machine learning validation using kNN and conditional probability algorithms.
Mixed datasets consist of both numeric and categorical attributes. Various k-means-based clustering algorithms have been developed for these datasets. Generally, these algorithms use random partition as a starting point, which tends to produce different clustering results for different runs. In this paper, we propose, …
Algorithm learns arbitrary ReLU neurons under Gaussian inputs.
We develop a family of accelerated stochastic algorithms that minimize sums of convex functions. Our algorithms improve upon the fastest running time for empirical risk minimization (ERM), and in particular linear least-squares regression, across a wide range of problem settings. To achieve this, we establish a framewo…
This paper analyzes adaptive gradient algorithms for better performance in ill-conditioned problems.
A novel approach ODAR detects outliers for clustering.
Unified view of clustering algorithms presented.
A new adaptive initialization method for K-means improves clustering performance and reduces complexity.
The results from most machine learning experiments are used for a specific purpose and then discarded. This results in a significant loss of information and requires rerunning experiments to compare learning algorithms. This also requires implementation of another algorithm for comparison, that may not always be correc…
New simulation shows trading algorithms' performance varies with parallelism.
Data pruning algorithms struggle in high compression regimes, as shown by theoretical and empirical studies.
Recently manifold learning algorithm for dimensionality reduction attracts more and more interests, and various linear and nonlinear, global and local algorithms are proposed. The key step of manifold learning algorithm is the neighboring region selection. However, so far for the references we know, few of which propos…
We review three algorithms for Latent Dirichlet Allocation (LDA). Two of them are variational inference algorithms: Variational Bayesian inference and Online Variational Bayesian inference and one is Markov Chain Monte Carlo (MCMC) algorithm -- Collapsed Gibbs sampling. We compare their time complexity and performance.…
Improved first-order algorithm for entropy regularized OT with faster convergence.
Linear optimization is many times algorithmically simpler than non-linear convex optimization. Linear optimization over matroid polytopes, matching polytopes and path polytopes are example of problems for which we have simple and efficient combinatorial algorithms, but whose non-linear convex counterpart is harder and …
Proposes new genetic algorithm rule for market competition.
Paper analyzes stability and generalization of SCO algorithms.
Algorithm design is a laborious process and often requires many iterations of ideation and validation. In this paper, we explore automating algorithm design and present a method to learn an optimization algorithm, which we believe to be the first method that can automatically discover a better algorithm. We approach th…
Bandit algorithms struggle with consistent performance and robustness.
New bounds tighten the generalization error of Gibbs algorithm.
We develop a new compressive sensing (CS) inversion algorithm by utilizing the Gaussian mixture model (GMM). While the compressive sensing is performed globally on the entire image as implemented in our lensless camera, a low-rank GMM is imposed on the local image patches. This low-rank GMM is derived via eigenvalue th…
This paper addresses the problem of neighborhood selection for Gaussian graphical models. We present two heuristic algorithms: a forward-backward greedy algorithm for general Gaussian graphical models based on mutual information test, and a threshold-based algorithm for walk summable Gaussian graphical models. Both alg…
The main contribution of this paper is the development of a new decision tree algorithm. The proposed approach allows users to guide the algorithm through the data partitioning process. We believe this feature has many applications but in this paper we demonstrate how to utilize this algorithm to analyse data sets cont…
Stochastic EM with biased MCMC improves inference stability.
Local Linear embedding (LLE) is a popular dimension reduction method. In this paper, we first show LLE with nonnegative constraint is equivalent to the widely used Laplacian embedding. We further propose to iterate the two steps in LLE repeatedly to improve the results. Thirdly, we relax the kNN constraint of LLE and p…
This study validates BN structure learning algorithms under noisy data, revealing performance discrepancies.