English
Related papers

Related papers: A Sober Look at Spectral Learning

200 papers

This work studies the general principles of improving the learning of language models (LMs), which aims at reducing the necessary training steps for achieving superior performance. Specifically, we present a theory for the optimal learning…

Computation and Language · Computer Science 2024-03-05 Yuxian Gu , Li Dong , Yaru Hao , Qingxiu Dong , Minlie Huang , Furu Wei

Stochastic Maximum Likelihood (SML) is a popular direction of arrival (DOA) estimation technique in array signal processing. It is a parametric method that jointly estimates signal and instrument noise by maximum likelihood, achieving…

Applications · Statistics 2021-02-04 Matthieu Simeoni , Paul Hurley

In real-world applications with large state and action spaces, reinforcement learning (RL) typically employs function approximations to represent core components like the policies, value functions, and dynamics models. Although powerful…

Machine Learning · Computer Science 2026-01-29 Chenxiao Gao , Haotian Sun , Na Li , Dale Schuurmans , Bo Dai

Determinantal point processes (DPPs) have wide-ranging applications in machine learning, where they are used to enforce the notion of diversity in subset selection problems. Many estimators have been proposed, but surprisingly the basic…

Statistics Theory · Mathematics 2017-07-25 Victor-Emmanuel Brunel , Ankur Moitra , Philippe Rigollet , John Urschel

Recent advancements in large language models (LLMs) reveal a perplexing phenomenon in continual learning: despite extensive training, models experience significant performance declines, raising questions about task alignment and underlying…

Machine Learning · Computer Science 2025-01-24 Junhao Zheng , Xidi Cai , Shengjie Qiu , Qianli Ma

We consider the problem of parameter estimation using weakly supervised datasets, where a training sample consists of the input and a partially specified annotation, which we refer to as the output. The missing information in the annotation…

Machine Learning · Computer Science 2012-06-22 M. Pawan Kumar , Ben Packer , Daphne Koller

This work explores maximum likelihood optimization of neural networks through hypernetworks. A hypernetwork initializes the weights of another network, which in turn can be employed for typical functional tasks such as regression and…

Machine Learning · Statistics 2018-01-15 Abdul-Saboor Sheikh , Kashif Rasul , Andreas Merentitis , Urs Bergmann

Self-training is a powerful approach to deep learning. The key process is to find a pseudo-label for modeling. However, previous self-training algorithms suffer from the over-confidence issue brought by the hard labels, even some…

Computer Vision and Pattern Recognition · Computer Science 2024-05-03 Zijia Wang , Wenbin Yang , Zhisong Liu , Zhen Jia

We study 15 large language models (LLMs) fine-tuned for chat and find that their maximum softmax probabilities (MSPs) are consistently miscalibrated on multiple-choice Q&A. However, those MSPs might still encode useful uncertainty…

Computation and Language · Computer Science 2025-08-08 Benjamin Plaut , Nguyen X. Khanh , Tu Trinh

Common tasks encountered in epidemiology, including disease incidence estimation and causal inference, rely on predictive modeling. Constructing a predictive model can be thought of as learning a prediction function, i.e., a function that…

Methodology · Statistics 2024-08-20 Rachael V. Phillips , Mark J. van der Laan , Hana Lee , Susan Gruber

In this paper I address the practical concern of predicting how much training data is sufficient for a statistical language learning system. First, I briefly review earlier results and show how these can be combined to bound the expected…

cmp-lg · Computer Science 2008-02-03 Mark Lauer

Maximum pseudolikelihood (MPL) estimators are useful alternatives to maximum likelihood (ML) estimators when likelihood functions are more difficult to manipulate than their marginal and conditional components. Furthermore, MPL estimators…

Methodology · Statistics 2017-08-30 Hien D. Nguyen

Statistical learning (SL) includes methods that extract knowledge from complex data. SL methods beyond generalized linear models are being increasingly implemented in public health research and epidemiology because they can perform better…

The asymptotic variance of the maximum likelihood estimate is proved to decrease when the maximization is restricted to a subspace that contains the true parameter value. Maximum likelihood estimation allows a systematic fitting of…

Statistics Theory · Mathematics 2018-01-31 Marie Turčičová , Jan Mandel , Kryštof Eben

Various methods for solving the inverse reinforcement learning (IRL) problem have been developed independently in machine learning and economics. In particular, the method of Maximum Causal Entropy IRL is based on the perspective of entropy…

Machine Learning · Computer Science 2021-03-05 Navyata Sanghvi , Shinnosuke Usami , Mohit Sharma , Joachim Groeger , Kris Kitani

Data-driven machine learning models are being increasingly employed in several important inference problems in biology, chemistry, and physics which require learning over combinatorial spaces. Recent empirical evidence (see, e.g., [1], [2],…

Machine Learning · Statistics 2022-10-07 Amirali Aghazadeh , Nived Rajaraman , Tony Tu , Kannan Ramchandran

Expectation-Maximization (EM) algorithm is a widely used iterative algorithm for computing maximum likelihood estimate when dealing with Gaussian Mixture Model (GMM). When the sample size is smaller than the data dimension, this could lead…

Machine Learning · Statistics 2023-07-06 Pierre Houdouin , Matthieu Jonkcheere , Frederic Pascal

Over the last few years, there has been a surge in the use of learning techniques to improve the performance of optimization algorithms. In particular, the learning of branching rules in mixed integer linear programming has received a lot…

An interesting phenomenon arises: Empirical Risk Minimization (ERM) sometimes outperforms methods specifically designed for out-of-distribution tasks. This motivates an investigation into the reasons behind such behavior beyond algorithmic…

Machine Learning · Computer Science 2026-01-21 Hong Zheng , Fei Teng

The main question is: why and how can we ever predict based on a finite sample? The question is not answered by statistical learning theory. Here, I suggest that prediction requires belief in "predictability" of the underlying dependence,…

Machine Learning · Computer Science 2022-01-28 Marina Sapir
‹ Prev 1 8 9 10 Next ›