Cover Image

Understanding Adam Requires Better Rotation Dependent Assumptions

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Tianyue H., Maes, Lucas, Milligan, Alan, Jolicoeur-Martineau, Alexia, Mitliagkas, Ioannis, Scieur, Damien, Lacoste-Julien, Simon, Guille-Escuret, Charles
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Generating Tabular Data Using Heterogeneous Sequential Feature Forest Flow Matching
by: Akazan, Ange-Clément, et al.
Published: (2024)

Gradient Descent Is Optimal Under Lower Restricted Secant Inequality And Upper Error Bound
by: Guille-Escuret, Charles, et al.
Published: (2022)

A Study of Condition Numbers for First-Order Optimization
by: Guille-Escuret, Charles, et al.
Published: (2020)

Less is More: Recursive Reasoning with Tiny Networks
by: Jolicoeur-Martineau, Alexia
Published: (2025)

Multi-Agent Game Generation and Evaluation via Audio-Visual Recordings
by: Jolicoeur-Martineau, Alexia
Published: (2025)

CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning
by: Guille-Escuret, Charles, et al.
Published: (2022)

Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection
by: Guille-Escuret, Charles, et al.
Published: (2023)

PopulAtion Parameter Averaging (PAPA)
by: Jolicoeur-Martineau, Alexia, et al.
Published: (2023)

From Conformal Predictions to Confidence Regions
by: Guille-Escuret, Charles, et al.
Published: (2024)

Finite Sample Confidence Regions for Linear Regression Parameters Using Arbitrary Predictors
by: Guille-Escuret, Charles, et al.
Published: (2024)

Navigating Potholes with Geometry-Aware Sharpness Minimization
by: Dufort-Labbé, Simon, et al.
Published: (2026)

Probabilistic Tiny Recursive Model
by: Sghaier, Amin, et al.
Published: (2026)

Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees
by: Jolicoeur-Martineau, Alexia, et al.
Published: (2023)

One Pass Is Not Enough: Recursive Latent Refinement for Generative Models
by: Esmaeilzadeh, Mehdi, et al.
Published: (2026)

On the Sample Efficiency of Inverse Dynamics Models for Semi-Supervised Imitation Learning
by: Morin, Sacha, et al.
Published: (2026)

LoGAH: Predicting 774-Million-Parameter Transformers using Graph HyperNetworks with 1/100 Parameters
by: Zhou, Xinyu, et al.
Published: (2024)

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
by: Maes, Lucas, et al.
Published: (2026)

Reparametrizing Shampoo and SOAP for Subspace Basis Updates and BFloat16 Storage
by: Milligan, Alan, et al.
Published: (2026)

Any-Property-Conditional Molecule Generation with Self-Criticism using Spanning Trees
by: Jolicoeur-Martineau, Alexia, et al.
Published: (2024)

Generating $π$-Functional Molecules Using STGG+ with Active Learning
by: Jolicoeur-Martineau, Alexia, et al.
Published: (2025)

Ctrl-V: Higher Fidelity Video Generation with Bounding-Box Controlled Object Motion
by: Luo, Ge Ya, et al.
Published: (2024)

stable-worldmodel-v1: Reproducible World Modeling Research and Evaluation
by: Maes, Lucas, et al.
Published: (2026)

Beyond FVD: Enhanced Evaluation Metrics for Video Generation Quality
by: Luo, Ge Ya, et al.
Published: (2024)

Acceleration Methods
by: d'Aspremont, Alexandre, et al.
Published: (2021)

On PI Controllers for Updating Lagrange Multipliers in Constrained Optimization
by: Sohrabi, Motahareh, et al.
Published: (2024)

Feature learning as alignment: a structural property of gradient descent in non-linear neural networks
by: Beaglehole, Daniel, et al.
Published: (2024)

Performative Prediction with Neural Networks
by: Mofakhami, Mehrnaz, et al.
Published: (2023)

Dual Optimistic Ascent (PI Control) is the Augmented Lagrangian Method in Disguise
by: Ramirez, Juan, et al.
Published: (2025)

Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models
by: Kunstner, Frederik, et al.
Published: (2024)

Ctrl-Crash: Controllable Diffusion for Realistic Car Crashes
by: Gosselin, Anthony, et al.
Published: (2025)

Promoting Exploration in Memory-Augmented Adam using Critical Momenta
by: Malviya, Pranshu, et al.
Published: (2023)

Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependencies
by: Lachapelle, Sébastien, et al.
Published: (2024)

On Convergence of Adam for Stochastic Optimization under Relaxed Assumptions
by: Hong, Yusu, et al.
Published: (2024)

Interlayer phase coherence and composite fermions
by: Jolicoeur, Thierry
Published: (2025)

A Derandomization Framework for Structure Discovery: Applications in Neural Networks and Beyond
by: Tsikouras, Nikos, et al.
Published: (2025)

An Empirical Study of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibration
by: Naganuma, Hiroki, et al.
Published: (2023)

Towards efficient representation identification in supervised learning
by: Ahuja, Kartik, et al.
Published: (2022)

Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation
by: Mahajan, Divyat, et al.
Published: (2022)

Dynamics of SGD with Stochastic Polyak Stepsizes: Truly Adaptive Variants and Convergence to Exact Solution
by: Orvieto, Antonio, et al.
Published: (2022)

Position: Adopt Constraints Over Fixed Penalties in Deep Learning
by: Ramirez, Juan, et al.
Published: (2025)