English
Related papers

Related papers: Differentiable lower bound for expected BLEU score

200 papers

A differential dynamic programming (DDP)-based framework for inverse reinforcement learning (IRL) is introduced to recover the parameters in the cost function, system dynamics, and constraints from demonstrations. Different from existing…

Robotics · Computer Science 2024-07-30 Kun Cao , Xinhang Xu , Wanxin Jin , Karl H. Johansson , Lihua Xie

Rank-based metrics are some of the most widely used criteria for performance evaluation of computer vision models. Despite years of effort, direct optimization for these metrics remains a challenge due to their non-differentiable and…

Machine Learning · Computer Science 2024-12-16 Michal Rolínek , Vít Musil , Anselm Paulus , Marin Vlastelica , Claudio Michaelis , Georg Martius

Offline Reinforcement Learning (RL) aims to learn a near-optimal policy from a fixed dataset of transitions collected by another policy. This problem has attracted a lot of attention recently, but most existing methods with strong…

Machine Learning · Computer Science 2023-05-23 Germano Gabbianelli , Gergely Neu , Nneka Okolo , Matteo Papini

We study the problem of off-policy value evaluation in reinforcement learning (RL), where one aims to estimate the value of a new policy based on data collected by a different policy. This problem is often a critical step when applying RL…

Machine Learning · Computer Science 2016-05-27 Nan Jiang , Lihong Li

Diffusion policies have achieved superior performance in imitation learning and offline reinforcement learning (RL) due to their rich expressiveness. However, the conventional diffusion training procedure requires samples from target…

Machine Learning · Computer Science 2025-07-01 Haitong Ma , Tianyi Chen , Kai Wang , Na Li , Bo Dai

While local basis function (LBF) estimation algorithms, commonly used for identifying/tracking systems with time-varying parameters, demonstrate good performance under the assumption of normally distributed measurement noise, the estimation…

Signal Processing · Electrical Eng. & Systems 2025-04-01 Maciej Niedźwiecki , Artur Gańcza , Wojciech Żuławiński , Agnieszka Wyłomańska

For stochastic process models, parameter inference is often severely bottlenecked by computationally expensive likelihood functions. Simulation-based inference (SBI) bypasses this restriction by constructing amortized surrogate likelihoods,…

Machine Learning · Statistics 2026-05-26 Alexander Shen , Mikael Kuusela

Automatic evaluation metrics are crucial for advancing sign language translation (SLT). Current SLT evaluation metrics, such as BLEU and ROUGE, are only text-based, and it remains unclear to what extent text-based metrics can reliably…

Computation and Language · Computer Science 2025-11-17 Shakib Yazdani , Yasser Hamidullah , Cristina España-Bonet , Eleftherios Avramidis , Josef van Genabith

We study the problem of off-policy evaluation (OPE) in Reinforcement Learning (RL), where the aim is to estimate the performance of a new policy given historical data that may have been generated by a different policy, or policies. In…

Machine Learning · Computer Science 2019-12-16 Aurélien F. Bibaut , Ivana Malenica , Nikos Vlassis , Mark J. van der Laan

Recent strides in large language models (LLMs) have yielded remarkable performance, leveraging reinforcement learning from human feedback (RLHF) to significantly enhance generation and alignment capabilities. However, RLHF encounters…

Computation and Language · Computer Science 2024-05-31 Kuo Liao , Shuang Li , Meng Zhao , Liqun Liu , Mengge Xue , Zhenyu Hu , Honglin Han , Chengguo Yin

Loss functions drive the optimization of machine learning algorithms. The choice of a loss function can have a significant impact on the training of a model, and how the model learns the data. Binary classification is one of the major…

Machine Learning · Computer Science 2022-11-02 Rayan Wali

Pretraining sentence encoders with language modeling and related unsupervised tasks has recently been shown to be very effective for language understanding tasks. By supplementing language model-style pretraining with further training on…

Computation and Language · Computer Science 2019-03-01 Jason Phang , Thibault Févry , Samuel R. Bowman

In high-dimensional statistics, variable selection recovers the latent sparse patterns from all possible covariate combinations. This paper proposes a novel optimization method to solve the exact L0-regularized regression problem, which is…

Methodology · Statistics 2022-06-02 Mingzhang Yin , Nhat Ho , Bowei Yan , Xiaoning Qian , Mingyuan Zhou

Reinforcement learning (RL) for large language model reasoning is frequently hindered by signal loss, a phenomenon where standard uniform sampling with small group sizes fails to uncover informative learning signals for difficult prompts.…

Machine Learning · Computer Science 2025-12-08 Wei Xiong , Chenlu Ye , Baohao Liao , Hanze Dong , Xinxing Xu , Christof Monz , Jiang Bian , Nan Jiang , Tong Zhang

Seeking to improve model generalization, we consider a new approach based on distributionally robust learning (DRL) that applies stochastic gradient descent to the outer minimization problem. Our algorithm efficiently estimates the gradient…

Machine Learning · Statistics 2020-12-24 Soumyadip Ghosh , Mark Squillante

The effectiveness of Object Detection, one of the central problems in computer vision tasks, highly depends on the definition of the loss function - a measure of how accurately your ML model can predict the expected outcome. Conventional…

Computer Vision and Pattern Recognition · Computer Science 2022-05-26 Zhora Gevorgyan

Neural machine translation models are often biased toward the limited translation references seen during training. To amend this form of overfitting, in this paper we propose fine-tuning the models with a novel training objective based on…

Computation and Language · Computer Science 2021-06-07 Inigo Jauregi Unanue , Jacob Parnell , Massimo Piccardi

We consider the problem of estimating the expected value of information (the knowledge gradient) for Bayesian learning problems where the belief model is nonlinear in the parameters. Our goal is to maximize some metric, while simultaneously…

Machine Learning · Statistics 2016-11-23 Xinyu He , Warren B. Powell

This paper investigates the so-called reward-balancing methods, a novel class of algorithms for solving discounted-return reinforcement learning (RL) problems. These methods consist of iteratively adjusting the reward function to transform…

Optimization and Control · Mathematics 2026-04-23 Simone Baroncini , Bahman Gharesifard , Giuseppe Notarstefano

The Reduced Basis Method (RBM) is a rigorous model reduction approach for solving parametrized partial differential equations. It identifies a low-dimensional subspace for approximation of the parametric solution manifold that is embedded…

Numerical Analysis · Mathematics 2018-09-25 Yanlai Chen , Jiahua Jiang , Akil Narayan