English
Related papers

Related papers: Learning from many trajectories

200 papers

We present a system and a set of techniques for learning linear predictors with convex losses on terascale datasets, with trillions of features, {The number of features here refers to the number of non-zero entries in the data matrix.}…

Machine Learning · Computer Science 2013-07-15 Alekh Agarwal , Olivier Chapelle , Miroslav Dudik , John Langford

Virtually all machine learning tasks are characterized using some form of loss function, and "good performance" is typically stated in terms of a sufficiently small average loss, taken over the random draw of test data. While optimizing for…

Machine Learning · Statistics 2023-12-01 Matthew J. Holland , Kazuki Tanabe

We consider learning a predictive model to be subsequently used for a given downstream task (described by an algorithm) that requires access to the model evaluation. This task need not be prediction, and this situation is frequently…

Machine Learning · Computer Science 2025-06-05 Jianyuan Yin , Qianxiao Li

Meta-reinforcement learning typically requires orders of magnitude more samples than single task reinforcement learning methods. This is because meta-training needs to deal with more diverse distributions and train extra components such as…

Machine Learning · Computer Science 2021-03-12 Bernie Wang , Simon Xu , Kurt Keutzer , Yang Gao , Bichen Wu

A fundamental challenge in learning an unknown dynamical system is to reduce model uncertainty by making measurements while maintaining safety. We formulate a mathematical definition of what it means to safely learn a dynamical system by…

Optimization and Control · Mathematics 2024-06-11 Amir Ali Ahmadi , Abraar Chaudhry , Vikas Sindhwani , Stephen Tu

Meta-learning of shared initialization parameters has shown to be highly effective in solving few-shot learning tasks. However, extending the framework to many-shot scenarios, which may further enhance its practicality, has been relatively…

Machine Learning · Computer Science 2022-02-17 Jaewoong Shin , Hae Beom Lee , Boqing Gong , Sung Ju Hwang

One popular trend in meta-learning is to learn from many training tasks a common initialization for a gradient-based method that can be used to solve a new task with few samples. The theory of meta-learning is still in its early stages,…

Machine Learning · Computer Science 2020-02-27 Nikunj Saunshi , Yi Zhang , Mikhail Khodak , Sanjeev Arora

Benchmarking anomaly detection approaches for multivariate time series is a challenging task due to a lack of high-quality datasets. Current publicly available datasets are too small, not diverse and feature trivial anomalies, which hinders…

Machine Learning · Computer Science 2025-11-13 Lucas Correia , Jan-Christoph Goos , Thomas Bäck , Anna V. Kononova

Slow concept drift is a ubiquitous, yet under-studied problem in practical machine learning systems. In such settings, although recent data is more indicative of future data, naively prioritizing recent instances runs the risk of losing…

Machine Learning · Computer Science 2023-12-21 Nishant Jain , Pradeep Shenoy

Time-optimal trajectories drive quadrotors to their dynamic limits, but computing such trajectories involves solving non-convex problems via iterative nonlinear optimization, making them prohibitively costly for real-time applications. In…

Robotics · Computer Science 2025-06-18 Katherine Mao , Hongzhan Yu , Ruipeng Zhang , Igor Spasojevic , M Ani Hsieh , Sicun Gao , Vijay Kumar

A central goal of machine learning is generalization. While the No Free Lunch Theorem states that we cannot obtain theoretical guarantees for generalization without further assumptions, in practice we observe that simple models which…

Machine Learning · Computer Science 2025-06-04 Eric Elmoznino , Tom Marty , Tejas Kasetty , Leo Gagnon , Sarthak Mittal , Mahan Fathi , Dhanya Sridhar , Guillaume Lajoie

Meta-learning seeks to build algorithms that rapidly learn how to solve new learning problems based on previous experience. In this paper we investigate meta-learning in the setting of stochastic linear bandit tasks. We assume that the…

Machine Learning · Computer Science 2022-05-31 Leonardo Cella , Karim Lounici , Massimiliano Pontil

Bayesian networks are basic graphical models, used widely both in statistics and artificial intelligence. These statistical models of conditional independence structure are described by acyclic directed graphs whose nodes correspond to…

Optimization and Control · Mathematics 2010-12-01 Raymond Hemmecke , Silvia Lindner , Milan Studený

How many parameters are required for a model to execute a given task? It has been argued that large language models, pre-trained via self-supervised learning, exhibit emergent capabilities such as multi-step reasoning as their number of…

Machine Learning · Computer Science 2024-09-23 Ingvar Ziemann , Nikolai Matni , George J. Pappas

Learning the structure of dependencies among multiple random variables is a problem of considerable theoretical and practical interest. Within the context of Bayesian Networks, a practical and surprisingly successful solution to this…

Machine Learning · Computer Science 2021-01-20 Giulio Caravagna , Daniele Ramazzotti

Labeling training data is a key bottleneck in the modern machine learning pipeline. Recent weak supervision approaches combine labels from multiple noisy sources by estimating their accuracies without access to ground truth labels; however,…

Machine Learning · Statistics 2019-03-15 Paroma Varma , Frederic Sala , Ann He , Alexander Ratner , Christopher Ré

We consider linear models for stochastic dynamics. To any such model can be associated a network (namely a directed graph) describing which degrees of freedom interact under the dynamics. We tackle the problem of learning such a network…

Statistics Theory · Mathematics 2011-03-01 José Bento , Morteza Ibrahimi , Andrea Montanari

As hyperparameter tuning becomes increasingly costly at scale, efficient tuning methods are essential. Yet principles for guiding hyperparameter tuning remain limited. In this work, we seek to establish such principles by considering a…

Machine Learning · Computer Science 2025-09-30 Bingrui Li , Jiaxin Wen , Zhanpeng Zhou , Jun Zhu , Jianfei Chen

Existing approaches of prescriptive analytics -- where inputs of an optimization model can be predicted by leveraging covariates in a machine learning model -- often attempt to optimize the mean value of an uncertain objective. However,…

Machine Learning · Computer Science 2025-03-05 Dimitris Bertsimas , Benjamin Boucher

In real-world sequential decision making tasks like autonomous driving, robotics, and healthcare, learning from observed state-action trajectories is critical for tasks like imitation, classification, and clustering. For example,…

Machine Learning · Computer Science 2025-01-20 Zichang Ge , Changyu Chen , Arunesh Sinha , Pradeep Varakantham