English
Related papers

Related papers: Manifold Metric: A Loss Landscape Approach for Pre…

200 papers

In model-based reinforcement learning, most algorithms rely on simulating trajectories from one-step models of the dynamics learned on data. A critical challenge of this approach is the compounding of one-step prediction errors as the…

Machine Learning · Computer Science 2024-02-06 Abdelhakim Benechehab , Albert Thomas , Giuseppe Paolo , Maurizio Filippone , Balázs Kégl

Distribution regression seeks to estimate the conditional distribution of a multivariate response given a continuous covariate. This approach offers a more complete characterization of dependence than traditional regression methods.…

Statistics Theory · Mathematics 2025-06-10 Rong Tang , Yun Yang

The ability to explain decisions made by machine learning models remains one of the most significant hurdles towards widespread adoption of AI in highly sensitive areas such as medicine, cybersecurity or autonomous driving. Great interest…

Machine Learning · Computer Science 2024-12-17 Maximilian P Niroomand , David J Wales

We introduce a Loss Discounting Framework for model and forecast combination which generalises and combines Bayesian model synthesis and generalized Bayes methodologies. We use a loss function to score the performance of different models…

Methodology · Statistics 2024-03-29 Dawid Bernaciak , Jim E. Griffin

We study empirical scaling laws for language model performance on the cross-entropy loss. The loss scales as a power-law with model size, dataset size, and the amount of compute used for training, with some trends spanning more than seven…

Geometric properties of Transformer weights, particularly the unembedding matrix, have been widely useful in language model interpretability research. Yet, their utility for estimating downstream performance remains unclear. In this work,…

Computation and Language · Computer Science 2026-02-25 Atharva Kulkarni , Jacob Mitchell Springer , Arjun Subramonian , Swabha Swayamdipta

With the widespread deployment of deep learning models, they influence their environment in various ways. The induced distribution shifts can lead to unexpected performance degradation in deployed models. Existing methods to anticipate…

We take a Bayesian perspective to illustrate a connection between training speed and the marginal likelihood in linear models. This provides two major insights: first, that a measure of a model's training speed can be used to estimate its…

Machine Learning · Computer Science 2020-10-28 Clare Lyle , Lisa Schut , Binxin Ru , Yarin Gal , Mark van der Wilk

Representation learning is typically applied to only one mode of a data matrix, either its rows or columns. Yet in many applications, there is an underlying geometry to both the rows and the columns. We propose utilizing this coupled…

Machine Learning · Statistics 2018-10-17 Gal Mishne , Eric C. Chi , Ronald R. Coifman

Model-based offline reinforcement learning approaches generally rely on bounds of model error. Estimating these bounds is usually achieved through uncertainty estimation methods. In this work, we combine parametric and nonparametric methods…

Machine Learning · Computer Science 2022-11-07 Guy Tennenholtz , Shie Mannor

Manifolds discovered by machine learning models provide a compact representation of the underlying data. Geodesics on these manifolds define locally length-minimising curves and provide a notion of distance, which are key for reduced-order…

Computational Geometry · Computer Science 2023-11-03 Daniel Kelshaw , Luca Magri

Structured prediction provides a general framework to deal with supervised problems where the outputs have semantically rich structure. While classical approaches consider finite, albeit potentially huge, output spaces, in this paper we…

Machine Learning · Statistics 2018-06-27 Alessandro Rudi , Carlo Ciliberto , Gian Maria Marconi , Lorenzo Rosasco

In this paper we study a model-based approach to calculating approximately optimal policies in Markovian Decision Processes. In particular, we derive novel bounds on the loss of using a policy derived from a factored linear model, a class…

Machine Learning · Statistics 2016-09-22 Bernardo Ávila Pires , Csaba Szepesvári

There is increasing interest in the problem of nonparametric regression with high-dimensional predictors. When the number of predictors $D$ is large, one encounters a daunting problem in attempting to estimate a $D$-dimensional surface…

Statistics Theory · Mathematics 2014-06-17 Yun Yang , David B. Dunson

Model-based reinforcement learning is one approach to increase sample efficiency. However, the accuracy of the dynamics model and the resulting compounding error over modelled trajectories are commonly regarded as key limitations. A natural…

Machine Learning · Computer Science 2023-03-08 Daniel Palenicek , Michael Lutter , Joao Carvalho , Jan Peters

For many machine learning tasks, the input data lie on a low-dimensional manifold embedded in a high dimensional space and, because of this high-dimensional structure, most algorithms are inefficient. The typical solution is to reduce the…

Machine Learning · Computer Science 2019-03-05 Anna C. Gilbert , Rishi Sonthalia

The exploration of complex physical or technological processes usually requires exploiting available information from different sources: (i) physical laws often represented as a family of parameter dependent partial differential equations…

Numerical Analysis · Mathematics 2020-02-04 Albert Cohen , Wolfgang Dahmen , Ron DeVore

There has been an emerging trend in non-Euclidean statistical analysis of aiming to recover a low dimensional structure, namely a manifold, underlying the high dimensional data. Recovering the manifold requires the noise to be of certain…

Machine Learning · Statistics 2024-06-11 Zhigang Yao , Yuqing Xia

Utilizing task-invariant knowledge acquired from related tasks as prior information, meta-learning offers a principled approach to learning a new task with limited data records. Sample-efficient adaptation of this prior information is a…

Machine Learning · Computer Science 2025-09-03 Yilang Zhang , Bingcong Li , Georgios B. Giannakis

Modern foundation models rely heavily on using scaling laws to guide crucial training decisions. Researchers often extrapolate the optimal architecture and hyper parameters settings from smaller training runs by describing the relationship…

Machine Learning · Computer Science 2025-02-27 Margaret Li , Sneha Kudugunta , Luke Zettlemoyer
‹ Prev 1 3 4 5 6 7 10 Next ›