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.

168,786 papers · 148 categories

Trend · papers per month

59118176235 · Jun 202019922001200920172026
48 results for regularized MLE

Regularized MLE improves MoE models for high-dimensional data.

problem Modeling with high-dimensional predictors and feature selection.
method Gaussian gating network, 1\ell_1-regularized MLE, EM-Lasso algorithm, BIC-like criterion.
result Regularized MLE outperforms standard MLE in clustering and regression tasks.

The paper develops methods for high-dimensional inference in Markov random fields.

problem Statistical inference for high-dimensional Markov random fields.
method Markov Chain Monte Carlo Maximum Likelihood Estimation (MCMC-MLE) with Elastic-net regularization.
result The proposed methods achieve 1\ell_{1}-consistency and false discovery rate control.

The paper strengthens the classical result of MLE convergence to a Gaussian distribution.

problem The classical result of MLE convergence to a Gaussian distribution.
method Sub-Gaussian concentration and entropic normality of the normalized MLE.
result Entropic central limit theorem for a smoothed version of the estimator.

Maximum Likelihood Estimators (MLE) has many good properties. For example, the asymptotic variance of MLE solution attains equality of the asymptotic Cram{é}r-Rao lower bound (efficiency bound), which is the minimum possible variance for an unbiased estimator. However, obtaining such MLE solution requires calculating t…

2018-05-18abs ↗pdf ↗

The paper improves ranking by integrating covariates and sparse intrinsic scores.

problem Ranking items with incomplete preference scores explained by covariates.
method Extends BTL model with covariate information and sparse intrinsic scores, using penalized MLE.
result Developed debiased estimator for penalized MLE with distributional properties.

Paper proposes an alternative to MLE for GLMs with non-canonical link functions.

problem Challenges in MLE for GLMs with non-canonical link functions.
method Variational Inequality (VI) estimation framework.
result Established finite-sample error bounds and asymptotic normality for VI estimator.

MLE and CVE are equivalent under exponential families, leading to faster and more stable EM algorithms.

problem Finding maximum likelihood estimators (MLE) efficiently and stably.
method Proved equivalence between MLE and CVE under exponential families, leading to an EM algorithm.
result EM algorithm achieves the same asymptotic variance as MLE and is faster and more stable.

Estimates network structure from correlated node outputs of wide-sense stationary processes.

problem Learning edge connectivity from node outputs of latent inputs.
method Wide-sense stationary stochastic processes, Laplacian matrix estimation, ℓ1-regularized Whittle's MLE.
result The MLE recovers the sparsity pattern of the Laplacian matrix with high probability.

We describe kk-MLE, a fast and efficient local search algorithm for learning finite statistical mixtures of exponential families such as Gaussian mixture models. Mixture models are traditionally learned using the expectation-maximization (EM) soft clustering technique that monotonically increases the incomplete (expec…

2012-03-23abs ↗pdf ↗

Optimizes ranking of top-k players from partial comparison data.

problem Identifying the top-k players from incomplete pairwise comparisons.
method Maximum Likelihood Estimator (MLE) and Spectral Method.
result MLE achieves optimal partial and exact recovery, while Spectral Method is sub-optimal.

The paper analyzes RLHF with human feedback and provides convergence results for MLE and pessimistic MLE.

problem Improving RLHF with human feedback from pairwise or KK-wise comparisons.
method Theoretical framework for RLHF with convergence analysis of MLE and pessimistic MLE.
result MLE fails but pessimistic MLE provides improved policies under certain coverage assumptions.

This paper improves topic model estimation for sparse distributions and applies it to Wasserstein distances.

problem Estimating sparse topic distributions in topic models with high-dimensional data.
method MLE for topic weights when AA is known, plug-in estimator for unknown AA.
result MLE can be exactly sparse and contain true zero pattern of topic weights.

Unified framework for shrinkage, thresholding, and regularization in normal mean estimation and linear regression.

problem Estimation of normal mean in multivariate settings with correlated observations.
method Approximate risk minimization over a functional class of shrinkage-thresholding rules.
result Unified estimator NOMAD for shrinkage, thresholding, and regularization.

The paper derives upper bounds on the MLE error for BTL model under general graphs.

problem Estimating the MLE of BTL model parameters with \ell_{\infty}-loss under general graphs.
method Novel upper bounds on \ell_{\infty} estimation error dependent on algebraic connectivity and graph topology.
result Upper bounds on \ell_{\infty} error are sharp and match minimax lower bounds under certain graph topologies.

New approach uses inverse reinforcement learning to improve language model training.

problem Training large language models using imitation learning methods.
method Developed a new method of inverse reinforcement learning to optimize sequences directly.
result IRL-based fine-tuning leads to better performance and diversity in language generation.

Paper establishes MLE consistency for market microstructure models.

problem Estimating parameters in partially observed diffusion models.
method Tractable sufficient condition for MLE consistency based on stationary distribution.
result Maximum likelihood estimators are consistent for market microstructure parameters.

Image-to-image networks speed up SAR model parameter estimation.

problem Computational infeasibility of MLE for large, non-stationary spatial fields.
method Used image-to-image networks to estimate SAR model parameters.
result Image-to-image networks enable faster and more accurate parameter estimation.

Simple Deep LDA models achieve accuracy competitive with softmax baselines.

problem Training Deep LDA models by maximum likelihood estimation leads to overlapping or collapsed class clusters.
method Proposed a constrained Deep LDA formulation with geometric constraints to fix class means and covariance.
result MLE becomes stable under geometric constraints, yielding well-separated class clusters.

We have observed an interesting, yet unexplained, phenomenon: Semidefinite programming (SDP) based relaxations of maximum likelihood estimators (MLE) tend to be tight in recovery problems with noisy data, even when MLE cannot exactly recover the ground truth. Several results establish tightness of SDP based relaxations…

2014-04-10abs ↗pdf ↗

New estimators improve Rasch model item parameter estimation for sparse data.

problem Estimating item parameters in sparse Rasch model data.
method Random pairing maximum likelihood estimator (RP-MLE) and its bootstrapped variant (MRP-MLE).
result RP-MLE and MRP-MLE are minimax optimal and provide precise item parameter estimates.

This paper explores the preference-based top-KK rank aggregation problem. Suppose that a collection of items is repeatedly compared in pairs, and one wishes to recover a consistent ordering that emphasizes the top-KK ranked items, based on partially revealed preferences. We focus on the Bradley-Terry-Luce (BTL) model…

2015-04-27abs ↗pdf ↗

Advocates for MLE in regression and forecasting for better inductive biases and post-hoc optimization.

problem Designing effective loss functions for regression and forecasting.
method Maximum Likelihood Estimation (MLE) approach for regression and forecasting.
result MLE approach outperforms direct empirical risk minimization under certain conditions and for various datasets.

Develops new Markov processes with switching rates and past dependence.

problem Modeling processes with dynamic switching rates and path dependence.
method Introduces a new class of Markov jump processes with regime switching and path dependence. Derives distributional properties and maximum likelihood estimates.
result Maximum likelihood estimates of the process parameters are derived in closed form and have asymptotic normality.

Paper explores Elliptical Wishart distributions in signal processing and machine learning.

problem Estimating parameters of Elliptical Wishart distributions.
method Proposes fixed point and Riemannian optimization algorithms for maximum likelihood estimation.
result Characterizes existence, uniqueness, and convergence of the MLE.

Improved convergence rates for MLE in mixture models using penalized log-likelihood.

problem Convergence rates for MLE in finite mixture models.
method Penalizing log-likelihood to discourage vanishing mixing weights, using Wasserstein distance and new loss functions.
result Improved convergence rates for some mixture components, faster than traditional methods.

Distributed learning of probabilistic models from multiple data repositories with minimum communication is increasingly important. We study a simple communication-efficient learning framework that first calculates the local maximum likelihood estimates (MLE) based on the data subsets, and then combines the local MLEs t…

2014-10-09abs ↗pdf ↗

A new ranking model with dynamic covariates improves statistical analysis.

problem Statistical ranking with varying covariates across comparisons.
method Introduced a Plackett--Luce framework for covariate-assisted ranking, providing conditions for model identifiability and MLE existence, and developing an alternating maximization algorithm.
result Uniform consistency of the Maximum Likelihood Estimation (MLE) under suitable assumptions on graph design and covariates.

New study shows MLE can avoid model collapse with gradual synthetic data addition.

problem Model collapse in generative models trained on synthetic data.
method Theoretical study of maximum likelihood estimation (MLE) under iterative training with accumulating synthetic data.
result Non-asymptotic bounds show MLE can avoid model collapse even as real data fraction vanishes.