English
Related papers

Related papers: Alpha-divergence loss function for neural density …

200 papers

Distortion Risk Measures (DRMs) capture risk preferences in decision-making and serve as general criteria for managing uncertainty. This paper proposes gradient descent algorithms for DRM optimization based on two dual representations: the…

Machine Learning · Computer Science 2025-10-07 Jinyang Jiang , Bernd Heidergott , Jiaqiao Hu , Yijie Peng

Estimation of density derivatives is a versatile tool in statistical data analysis. A naive approach is to first estimate the density and then compute its derivative. However, such a two-step approach does not work well because a good…

Machine Learning · Statistics 2014-07-01 Hiroaki Sasaki , Yung-Kyun Noh , Masashi Sugiyama

To address the needs of modeling uncertainty in sensitive machine learning applications, the setup of distributionally robust optimization (DRO) seeks good performance uniformly across a variety of tasks. The recent multi-distribution…

Machine Learning · Statistics 2026-01-01 Rafael Hanashiro , Patrick Jaillet

We study constrained reinforcement learning (CRL) from a novel perspective by setting constraints directly on state density functions, rather than the value functions considered by previous works. State density has a clear physical and…

Machine Learning · Computer Science 2021-06-25 Zengyi Qin , Yuxiao Chen , Chuchu Fan

Differential learning rate (DLR), a technique that applies different learning rates to different model parameters, has been widely used in deep learning and achieved empirical success via its various forms. For example, parameter-efficient…

Machine Learning · Computer Science 2025-05-20 Shiyun Xu , Zhiqi Bu , Yiliang Zhang , Ian Barnett

In real life, we frequently come across data sets that involve some independent explanatory variable(s) generating a set of ordinal responses. These ordinal responses may correspond to an underlying continuous latent variable, which is…

Methodology · Statistics 2024-01-08 Arijit Pyne , Subhrajyoty Roy , Abhik Ghosh , Ayanendranath Basu

Generative Flow Networks (GFlowNets) are amortized inference models designed to sample from unnormalized distributions over composable objects, with applications in generative modeling for tasks in fields such as causal discovery, NLP, and…

Machine Learning · Computer Science 2026-04-13 Tiago da Silva , Eliezer de Souza da Silva , Diego Mesquita

In this paper, we develop a novel efficient and robust nonparametric regression estimator under a framework of feedforward neural network. There are several interesting characteristics for the proposed estimator. First, the loss function is…

Methodology · Statistics 2023-09-25 Xuancheng Wang , Ling Zhou , Huazhen Lin

Number prediction stands as a fundamental capability of large language models (LLMs) in mathematical problem-solving and code generation. The widely adopted maximum likelihood estimation (MLE) for LLM training is not tailored to number…

Computation and Language · Computer Science 2026-05-21 Zhaohui Zheng , Chenhang He , Shihao Wang , Yuxuan Li , Ming-Ming Cheng , Lei Zhang

Estimating uncertainty in deep learning models is critical for reliable decision-making in high-stakes applications such as medical imaging. Prior research has established that the difference between an input sample and its reconstructed…

Machine Learning · Computer Science 2026-01-28 Xinran Xu , Li Rong Wang , Xiuyi Fan

Reinforcement Learning with Human Feedback (RLHF) has become crucial for aligning Large Language Models (LLMs) with human intent. However, existing offline RLHF approaches suffer from overoptimization, where language models degrade by…

Machine Learning · Computer Science 2026-04-20 Sharan Sahu , Martin T. Wells

The aim of this paper is to study different estimation procedures based on $\varphi-$divergences. The dual representation of $\varphi-$divergences based on the Fenchel-Legendre duality is the main interest of this study. It provides a way…

Methodology · Statistics 2015-10-13 Diaa Al Mohamad

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to auto-regressive (AR) models, offering greater expressive capacity and potential for parallel generation and faster inference. However, open-source dLLMs…

Machine Learning · Computer Science 2026-05-12 Natalia Frumkin , Bokun Wang , Hung-Yueh Chiang , Chi-Chih Chang , Mohamed S. Abdelfattah , Diana Marculescu

Robustness to noise and outliers is a desirable trait in phase retrieval algorithms for many applications in imaging and signal processing. In this paper, we develop novel robust phase retrieval algorithms based on the minimization of…

Signal Processing · Electrical Eng. & Systems 2024-02-15 Nazia Afroz Choudhury , Bariscan Yonel , Birsen Yazici

Value function learning plays a central role in many state-of-the-art reinforcement-learning algorithms. Many popular algorithms like Q-learning do not optimize any objective function, but are fixed-point iterations of some variant of…

Machine Learning · Computer Science 2020-01-10 Yihao Feng , Lihong Li , Qiang Liu

Deformable medical image registration is a fundamental task in medical image analysis. While deep learning-based methods have demonstrated superior accuracy and computational efficiency compared to traditional techniques, they often…

Computer Vision and Pattern Recognition · Computer Science 2025-10-23 Ahsan Raza Siyal , Markus Haltmeier , Ruth Steiger , Malik Galijasevic , Elke Ruth Gizewski , Astrid Ellen Grams

Test-time reinforcement learning (TTRL) enables large language models (LLMs) to self-improve on unlabeled inputs, but its effectiveness critically depends on how reward signals are estimated without ground-truth supervision. Most existing…

Computation and Language · Computer Science 2026-01-30 Bodong Du , Xuanqi Huang , Xiaomeng Li

Distributionally robust optimization (DRO) has attracted attention in machine learning due to its connections to regularization, generalization, and robustness. Existing work has considered uncertainty sets based on phi-divergences and…

Machine Learning · Computer Science 2019-05-28 Matthew Staib , Stefanie Jegelka

Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to propose candidate tokens that are then verified in parallel by the target model. The speedup is significantly…

Machine Learning · Computer Science 2026-03-02 Alexander Samarin , Sergei Krutikov , Anton Shevtsov , Sergei Skvortsov , Filipp Fisin , Alexander Golubev

Utilizing text-only data with an external language model (ELM) in end-to-end RNN-Transducer (RNN-T) for speech recognition is challenging. Recently, a class of methods such as density ratio (DR) and internal language model estimation (ILME)…

Audio and Speech Processing · Electrical Eng. & Systems 2022-08-04 Huahuan Zheng , Keyu An , Zhijian Ou , Chen Huang , Ke Ding , Guanglu Wan
‹ Prev 1 3 4 5 6 7 10 Next ›