Copertina

Overshoot: Taking advantage of future gradients in momentum-based stochastic optimization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kopal, Jakub, Gregor, Michal, de Leon-Martinez, Santiago, Simko, Jakub
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Interpretable Predictability-Based AI Text Detection: A Replication Study
di: Skurla, Adam, et al.
Pubblicazione: (2026)

mcdok at SemEval-2026 Task 13: Finetuning LLMs for Detection of Machine-Generated Code
di: Skurla, Adam, et al.
Pubblicazione: (2026)

DelTriC: A Novel Clustering Method with Accurate Outlier
di: Javurek, Tomas, et al.
Pubblicazione: (2025)

Group-blind optimal transport to group parity and its constrained variants
di: Zhou, Quan, et al.
Pubblicazione: (2023)

CEAID: Benchmark of Multilingual Machine-Generated Text Detection Methods for Central European Languages
di: Macko, Dominik, et al.
Pubblicazione: (2025)

Acceleration of stochastic gradient descent with momentum by averaging: finite-sample rates and asymptotic normality
di: Tang, Kejie, et al.
Pubblicazione: (2023)

A stochastic gradient method for trilevel optimization
di: Giovannelli, Tommaso, et al.
Pubblicazione: (2025)

Towards Rational Pesticide Design with Graph Machine Learning Models for Ecotoxicology
di: Adamczyk, Jakub
Pubblicazione: (2025)

Generative AI Systems: A Systems-based Perspective on Generative AI
di: Tomczak, Jakub M.
Pubblicazione: (2024)

Better as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual Classification
di: Pecher, Branislav, et al.
Pubblicazione: (2026)

Online combinatorial optimization with stochastic decision sets and adversarial losses
di: Neu, Gergely, et al.
Pubblicazione: (2026)

Dealing with unbounded gradients in stochastic saddle-point optimization
di: Neu, Gergely, et al.
Pubblicazione: (2024)

Convergence rates of stochastic gradient method with independent sequences of step-size and momentum weight
di: Hwang, Wen-Liang
Pubblicazione: (2024)

Hierarchical VAE with a Diffusion-based VampPrior
di: Kuzina, Anna, et al.
Pubblicazione: (2024)

Evaluating machine learning models for predicting pesticide toxicity to honey bees
di: Adamczyk, Jakub, et al.
Pubblicazione: (2025)

SACn: Soft Actor-Critic with n-step Returns
di: Łyskawa, Jakub, et al.
Pubblicazione: (2025)

Cross-lingual Named Entity Corpus for Slavic Languages
di: Piskorski, Jakub, et al.
Pubblicazione: (2024)

Forecasting Probability Distributions of Financial Returns with Deep Neural Networks
di: Michańków, Jakub
Pubblicazione: (2025)

Performance and Efficiency of Climate In-Situ Data Reconstruction: Why Optimized IDW Outperforms kriging and Implicit Neural Representation
di: Walczak, Jakub
Pubblicazione: (2025)

Unregularized limit of stochastic gradient method for Wasserstein distributionally robust optimization
di: Le, Tam
Pubblicazione: (2025)

MolPILE -- large-scale, diverse dataset for molecular representation learning
di: Adamczyk, Jakub, et al.
Pubblicazione: (2025)

Plausible Counterfactual Explanations of Recommendations
di: Černý, Jakub, et al.
Pubblicazione: (2025)

Clustering-based hard negative sampling for supervised contrastive speaker verification
di: Masztalski, Piotr, et al.
Pubblicazione: (2025)

Spectral Map for Slow Collective Variables, Markovian Dynamics, and Transition State Ensembles
di: Rydzewski, Jakub
Pubblicazione: (2024)

Improving KAN with CDF normalization to quantiles
di: Strawa, Jakub, et al.
Pubblicazione: (2025)

Network Degeneracy as an Indicator of Training Performance: Comparing Finite and Infinite Width Angle Predictions
di: Jakub, Cameron, et al.
Pubblicazione: (2023)

An effect analysis of the balancing techniques on the counterfactual explanations of student success prediction models
di: Cavus, Mustafa, et al.
Pubblicazione: (2024)

Higher order definition of causality by optimally conditioned transfer entropy
di: Kořenek, Jakub, et al.
Pubblicazione: (2024)

Langevin dynamics based algorithm e-TH$\varepsilon$O POULA for stochastic optimization problems with discontinuous stochastic gradient
di: Lim, Dong-Young, et al.
Pubblicazione: (2022)

Sample Complexity of Bias Detection with Subsampled Point-to-Subspace Distances
di: Matilla, German Martinez, et al.
Pubblicazione: (2025)

A geometric framework for momentum-based optimizers for low-rank training
di: Schotthöfer, Steffen, et al.
Pubblicazione: (2025)

Task-Agnostic Contrastive Pretraining for Relational Deep Learning
di: Peleška, Jakub, et al.
Pubblicazione: (2025)

REDELEX: A Framework for Relational Deep Learning Exploration
di: Peleška, Jakub, et al.
Pubblicazione: (2025)

Depth Degeneracy in Neural Networks: Vanishing Angles in Fully Connected ReLU Networks on Initialization
di: Jakub, Cameron, et al.
Pubblicazione: (2023)

AMO Sampler: Enhancing Text Rendering with Overshooting
di: Hu, Xixi, et al.
Pubblicazione: (2024)

Equivalence of stochastic and deterministic policy gradients
di: Todorov, Emo
Pubblicazione: (2025)

Distributional value gradients for stochastic environments
di: Debes, Baptiste, et al.
Pubblicazione: (2026)

Knowledge Graph-extended Retrieval Augmented Generation for Question Answering
di: Linders, Jasper, et al.
Pubblicazione: (2025)

A Generative-AI-Driven Claim Retrieval System Capable of Detecting and Retrieving Claims from Social Media Platforms in Multiple Languages
di: Vykopal, Ivan, et al.
Pubblicazione: (2025)

Unraveling the Mechanism of Drug Binding to SARS-CoV-2 RNA Pseudoknot with Thermodynamics-Driven Machine Learning
di: Ivonina, Mariia, et al.
Pubblicazione: (2026)