English
Related papers

Related papers: Drifting Fields are not Conservative

200 papers

Recent studies show that transformer-based architectures emulate gradient descent during a forward pass, contributing to in-context learning capabilities - an ability where the model adapts to new tasks based on a sequence of prompt…

Statistics Theory · Mathematics 2024-05-13 Karthik Duraisamy

Current expectations from training deep learning models with gradient-based methods include: 1) transparency; 2) high convergence rates; 3) high inductive biases. While the state-of-art methods with adaptive learning rate schedules are…

Machine Learning · Computer Science 2020-08-11 Ilona Kulikovskikh , Tarzan Legović

Real-world datasets often exhibit temporal dynamics characterized by evolving data distributions. Disregarding this phenomenon, commonly referred to as concept drift, can significantly diminish a model's predictive accuracy. Furthermore,…

Machine Learning · Computer Science 2026-05-28 Mohammad Abu-Shaira , Ajita Rattani , Weishi Shi

A central challenge in Bayesian inference is efficiently approximating posterior distributions. Stein Variational Gradient Descent (SVGD) is a popular variational inference method which transports a set of particles to approximate a target…

Machine Learning · Statistics 2025-12-05 Moritz Melcher , Simon Weissmann , Ashia C. Wilson , Jakob Zech

Distributionally-robust optimization is often studied for a fixed set of distributions rather than time-varying distributions that can drift significantly over time (which is, for instance, the case in finance and sociology due to…

Optimization and Control · Mathematics 2020-10-01 Iman Shames , Farhad Farokhi

We introduce an adaptive method with formal quality guarantees for weak supervision in a non-stationary setting. Our goal is to infer the unknown labels of a sequence of data by using weak supervision sources that provide independent noisy…

Machine Learning · Computer Science 2025-05-05 Alessio Mazzetto , Reza Esfandiarpoor , Akash Singirikonda , Eli Upfal , Stephen H. Bach

Variational quantum circuits have arisen as an important method in quantum computing. A crucial step of it is parameter optimization, which is typically tackled through gradient-descent techniques. We advantageously explore instead the use…

Quantum Physics · Physics 2024-12-24 Vignesh Anantharamakrishnan , Márcio M. Taddei

Recent work on background subtraction has shown developments on two major fronts. In one, there has been increasing sophistication of probabilistic models, from mixtures of Gaussians at each pixel [7], to kernel density estimates at each…

Computer Vision and Pattern Recognition · Computer Science 2016-11-17 Manjunath Narayana , Allen Hanson , Erik Learned-Miller

In classical external gauge fields that fall off less fast than the inverse of the evolution parameter (time) of the system the implementability of a unitary perturbative scattering operator ($S$-matrix) is not guaranteed, although the…

High Energy Physics - Theory · Physics 2008-11-26 Dennis D. Dietrich

Using the notion of conservative gradient, we provide a simple model to estimate the computational costs of the backward and forward modes of algorithmic differentiation for a wide class of nonsmooth programs. The overhead complexity of the…

Numerical Analysis · Mathematics 2023-02-07 Jérôme Bolte , Ryan Boustany , Edouard Pauwels , Béatrice Pesquet-Popescu

Learning rules -- prescriptions for updating model parameters to improve performance -- are typically assumed rather than derived. Why do some learning rules work better than others, and under what assumptions can a given rule be considered…

Machine Learning · Computer Science 2025-11-03 John J. Vastola , Samuel J. Gershman , Kanaka Rajan

We consider passive scalar convected by multi-scale random velocity field with short yet finite temporal correlations. Taking Kraichnan's limit of a white Gaussian velocity as a zero approximation we develop perturbation theory with respect…

chao-dyn · Physics 2009-10-28 M. Chertkov , G. Falkovich , V. Lebedev

Inflation can be supported in very steep potentials if it is generated by rapidly turning fields, which can be natural in negatively curved field spaces. The curvature perturbation, $\zeta$, of these models undergoes an exponential,…

High Energy Physics - Theory · Physics 2019-12-18 Theodor Bjorkmo , Ricardo Z. Ferreira , M. C. David Marsh

Among dissimilarities between probability distributions, the Kernel Stein Discrepancy (KSD) has received much interest recently. We investigate the properties of its Wasserstein gradient flow to approximate a target probability distribution…

Machine Learning · Statistics 2021-05-24 Anna Korba , Pierre-Cyril Aubin-Frankowski , Szymon Majewski , Pierre Ablin

Cuscuton Gravity is characterized as a scalar field that can be added to general relativity without introducing any new dynamical degrees of freedom on a cosmological background. Yet, it modifies gravity such that spacetime singularities…

High Energy Physics - Theory · Physics 2025-05-19 Amir Dehghani , Ghazal Geshnizjani , Jerome Quintin

Several emerging post-Bayesian methods target a probability distribution for which an entropy-regularised variational objective is minimised. This increased flexibility introduces a computational challenge, as one loses access to an…

Computation · Statistics 2025-12-17 Clémentine Chazal , Heishiro Kanagawa , Zheyang Shen , Anna Korba , Chris. J. Oates

Discrete flow-based models are a recently proposed class of generative models that learn invertible transformations for discrete random variables. Since they do not require data dequantization and maximize an exact likelihood objective,…

Machine Learning · Computer Science 2021-07-27 Alexandra Lindt , Emiel Hoogeboom

Current open-loop trajectory models struggle in real-world autonomous driving because minor initial deviations often cascade into compounding errors, pushing the agent into out-of-distribution states. While fully differentiable closed-loop…

Robotics · Computer Science 2026-03-25 Harsh Yadav , Christian Bohn , Tobias Meisen

We discuss mimetic gravity theories with direct couplings between the curvature and higher derivatives of the scalar field, up to the quintic order, which were proposed to solve the instability problem for linear perturbations around the…

General Relativity and Quantum Cosmology · Physics 2019-12-18 Alexander Ganz , Nicola Bartolo , Sabino Matarrese

This research proposes a novel drift detection methodology for machine learning (ML) models based on the concept of ''deformation'' in the vector space representation of data. Recognizing that new data can act as forces stretching,…

Machine Learning · Computer Science 2024-11-06 Giancarlo Cobino , Simone Farci