English
Related papers

Related papers: Per-Domain Generalizing Policies: On Validation In…

200 papers

With the rise of stochastic generative models in robot policy learning, end-to-end visuomotor policies are increasingly successful at solving complex tasks by learning from human demonstrations. Nevertheless, since real-world evaluation…

Robotics · Computer Science 2024-10-24 Joseph A. Vincent , Haruki Nishimura , Masha Itkina , Paarth Shah , Mac Schwager , Thomas Kollar

This paper focuses on understanding how the generalization error scales with the amount of the training data for deep neural networks (DNNs). Existing techniques in statistical learning require computation of capacity measures, such as VC…

Machine Learning · Computer Science 2021-05-06 Devansh Bisla , Apoorva Nandini Saridena , Anna Choromanska

Evaluating the in-context learning classification performance of language models poses challenges due to small dataset sizes, extensive prompt-selection using the validation set, and intentionally difficult tasks that lead to near-random…

Computation and Language · Computer Science 2024-11-12 Gregory Yauney , David Mimno

Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset, making it applicable in a variety of real-world scenarios. Existing SFDA methods ONLY assess…

Computer Vision and Pattern Recognition · Computer Science 2023-10-10 Longxiang Tang , Kai Li , Chunming He , Yulun Zhang , Xiu Li

Generative Flow Networks (GFlowNets) have emerged as an innovative learning paradigm designed to address the challenge of sampling from an unnormalized probability distribution, called the reward function. This framework learns a policy on…

Machine Learning · Computer Science 2024-07-04 Anas Krichel , Nikolay Malkin , Salem Lahlou , Yoshua Bengio

Generative models typically sample outputs independently, and recent inference-time guidance and scaling algorithms focus on improving the quality of individual samples. However, in real-world applications, users are often presented with a…

Computer Vision and Pattern Recognition · Computer Science 2025-08-22 Gaurav Parmar , Or Patashnik , Daniil Ostashev , Kuan-Chieh Wang , Kfir Aberman , Srinivasa Narasimhan , Jun-Yan Zhu

Commonly used optimization algorithms often show a trade-off between good generalization and fast training times. For instance, stochastic gradient descent (SGD) tends to have good generalization; however, adaptive gradient methods have…

Machine Learning · Computer Science 2023-06-14 Aditya Cowsik , Tankut Can , Paolo Glorioso

Graph Neural Networks (GNNs) are a new and increasingly popular family of deep neural network architectures to perform learning on graphs. Training them efficiently is challenging due to the irregular nature of graph data. The problem…

Machine Learning · Computer Science 2021-06-15 Marco Serafini , Hui Guan

Penetration testing, the simulation of cyberattacks to identify security vulnerabilities, presents a sequential decision-making problem well-suited for reinforcement learning (RL) automation. Like many applications of RL to real-world…

Machine Learning · Computer Science 2025-09-25 Raphael Simon , Pieter Libin , Wim Mees

Scaling laws guide large language model training by relating compute to cross-entropy loss, and recent work further extends them to predict downstream benchmark performance. However, prior approaches face generalization limitations from two…

Computation and Language · Computer Science 2026-05-28 Quanen Sun , Changxin Tian , Ke Shi , Cai Chen , Cunyin Peng , Jia Liu , Kunlong Chen , Zhiqiang Zhang

Recently, significant progress has been made in understanding the generalization of neural networks (NNs) trained by gradient descent (GD) using the algorithmic stability approach. However, most of the existing research has focused on…

Machine Learning · Computer Science 2025-07-22 Puyu Wang , Yunwen Lei , Di Wang , Yiming Ying , Ding-Xuan Zhou

Policy gradient methods hold great potential for solving complex continuous control tasks. Still, their training efficiency can be improved by exploiting structure within the optimization problem. Recent work indicates that supervised…

Machine Learning · Computer Science 2024-03-19 Jan Schneider , Pierre Schumacher , Simon Guist , Le Chen , Daniel Häufle , Bernhard Schölkopf , Dieter Büchler

The increasing use of deep neural networks for safety-critical applications, such as autonomous driving and flight control, raises concerns about their safety and reliability. Formal verification can address these concerns by guaranteeing…

Artificial Intelligence · Computer Science 2018-02-06 Lindsey Kuper , Guy Katz , Justin Gottschlich , Kyle Julian , Clark Barrett , Mykel Kochenderfer

Local decision rules are commonly understood to be more explainable, due to the local nature of the patterns involved. With numerical optimization methods such as gradient boosting, ensembles of local decision rules can gain good predictive…

Machine Learning · Computer Science 2025-08-27 Xin Du , Subramanian Ramamoorthy , Wouter Duivesteijn , Jin Tian , Mykola Pechenizkiy

Generalized planning is concerned with the characterization and computation of plans that solve many instances at once. In the standard formulation, a generalized plan is a mapping from feature or observation histories into actions,…

Artificial Intelligence · Computer Science 2018-06-15 Blai Bonet , Hector Geffner

Deep reinforcement learning (RL) agents often fail to generalize to unseen scenarios, even when they are trained on many instances of semantically similar environments. Data augmentation has recently been shown to improve the sample…

Machine Learning · Computer Science 2021-02-23 Roberta Raileanu , Max Goldstein , Denis Yarats , Ilya Kostrikov , Rob Fergus

Dynamic Algorithm Configuration (DAC) addresses the challenge of dynamically setting hyperparameters of an algorithm for a diverse set of instances rather than focusing solely on individual tasks. Agents trained with Deep Reinforcement…

Machine Learning · Computer Science 2024-07-19 Carolin Benjamins , Gjorgjina Cenikj , Ana Nikolikj , Aditya Mohan , Tome Eftimov , Marius Lindauer

Preprocessing data is an important step before any data analysis. In this paper, we focus on one particular aspect, namely scaling or normalization. We analyze various scaling methods in common use and study their effects on different…

Machine Learning · Statistics 2017-09-05 Ting Li , Bingyi Jing , Ningchen Ying , Xianshi Yu

Decoding strategies largely determine the quality of Large Language Model (LLM) outputs, yet widely used heuristics such as greedy or fixed temperature/top-p decoding are static and often task-agnostic, leading to suboptimal or inconsistent…

Computation and Language · Computer Science 2026-03-20 Asmita Bhardwaj , Yuya Jeremy Ong , Eelaaf Zahid , Basel Shbita

Policy gradient is a generic and flexible reinforcement learning approach that generally enjoys simplicity in analysis, implementation, and deployment. In the last few decades, this approach has been extensively advanced for fully…

Machine Learning · Computer Science 2020-05-26 Kamyar Azizzadenesheli , Yisong Yue , Animashree Anandkumar