Cover Image

The Role of Symmetry in Optimizing Overparameterized Networks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sareen, Kusha, Pedramfar, Mohammad, Kaba, Sékou-Oumar, Shakerinava, Mehran, Ravanbakhsh, Siamak
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Energy Loss Functions for Physical Systems
by: Kaba, Sékou-Oumar, et al.
Published: (2025)

Diffusion Tree Sampling: Scalable inference-time alignment of diffusion models
by: Jain, Vineet, et al.
Published: (2025)

Symmetry Breaking and Equivariant Neural Networks
by: Kaba, Sékou-Oumar, et al.
Published: (2023)

Symmetry-Aware Generative Modeling through Learned Canonicalization
by: Sareen, Kusha, et al.
Published: (2025)

Beyond Scalar Rewards: An Axiomatic Framework for Lexicographic MDPs
by: Shakerinava, Mehran, et al.
Published: (2025)

Inverting Data Transformations via Diffusion Sampling
by: Kim, Jinwoo, et al.
Published: (2026)

On the Identifiability of Causal Abstractions
by: Li, Xiusi, et al.
Published: (2025)

Multi-Armed Sampling Problem and the End of Exploration
by: Pedramfar, Mohammad, et al.
Published: (2025)

Scaling Laws and Symmetry, Evidence from Neural Force Fields
by: Ngo, Khang, et al.
Published: (2025)

The Expressive Limits of Diagonal SSMs for State-Tracking
by: Shakerinava, Mehran, et al.
Published: (2026)

Improving Equivariant Networks with Probabilistic Symmetry Breaking
by: Lawrence, Hannah, et al.
Published: (2025)

Weight-Sharing Regularization
by: Shakerinava, Mehran, et al.
Published: (2023)

Learning to Reach Goals via Diffusion
by: Jain, Vineet, et al.
Published: (2023)

SymmCD: Symmetry-Preserving Crystal Generation with Diffusion Models
by: Levy, Daniel, et al.
Published: (2025)

$γ$-weakly $θ$-up-concavity: A Unified Framework for Non-Convex Optimization Beyond DR-Submodular and OSS Functions
by: Pedramfar, Mohammad, et al.
Published: (2026)

Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers
by: Sareen, Kusha, et al.
Published: (2025)

On Diffusion Modeling for Anomaly Detection
by: Livernoche, Victor, et al.
Published: (2023)

BAGEL: Projection-Free Algorithm for Adversarially Constrained Online Convex Optimization
by: Lu, Yiyang, et al.
Published: (2025)

Stochastic Submodular Bandits with Delayed Composite Anonymous Bandit Feedback
by: Pedramfar, Mohammad, et al.
Published: (2023)

Efficient Dynamics Modeling in Interactive Environments with Koopman Theory
by: Mondal, Arnab Kumar, et al.
Published: (2023)

Parity Requires Unified Input Dependence and Negative Eigenvalues in SSMs
by: Khavari, Behnoush, et al.
Published: (2025)

Improved Bayesian Regret Bounds for Thompson Sampling in Reinforcement Learning
by: Moradipari, Ahmadreza, et al.
Published: (2023)

A Unified Approach for Maximizing Continuous DR-submodular Functions
by: Pedramfar, Mohammad, et al.
Published: (2023)

Local Inconsistency Resolution: The Interplay between Attention and Control in Probabilistic Models
by: Richardson, Oliver E., et al.
Published: (2026)

Machine Unlearning under Overparameterization
by: Block, Jacob L., et al.
Published: (2025)

Unified Projection-Free Algorithms for Adversarial DR-Submodular Optimization
by: Pedramfar, Mohammad, et al.
Published: (2024)

Provable Generalization in Overparameterized Neural Nets
by: Dhingra, Aviral
Published: (2025)

Knowledge Distillation on Spatial-Temporal Graph Convolutional Network for Traffic Prediction
by: Izadi, Mohammad, et al.
Published: (2024)

Towards Initialization-dependent and Non-vacuous Generalization Bounds for Overparameterized Shallow Neural Networks
by: Lei, Yunwen, et al.
Published: (2026)

ASDFormer: A Transformer with Mixtures of Pooling-Classifier Experts for Robust Autism Diagnosis and Biomarker Discovery
by: Izadi, Mohammad, et al.
Published: (2025)

A Diffusion-Contrastive Graph Neural Network with Virtual Nodes for Wind Nowcasting in Unobserved Regions
by: Shi, Jie, et al.
Published: (2026)

MAD-SmaAt-GNet: A Multimodal Advection-Guided Neural Network for Precipitation Nowcasting
by: van Wonderen, Samuel, et al.
Published: (2026)

Analysis of Overparameterization in Continual Learning under a Linear Model
by: Goldfarb, Daniel, et al.
Published: (2025)

Large Language Models Are Overparameterized Text Encoders
by: K, Thennal D, et al.
Published: (2024)

EEG-MFTNet: An Enhanced EEGNet Architecture with Multi-Scale Temporal Convolutions and Transformer Fusion for Cross-Session Motor Imagery Decoding
by: Andrikopoulos, Panagiotis, et al.
Published: (2026)

SmaAT-QMix-UNet: A Parameter-Efficient Vector-Quantized UNet for Precipitation Nowcasting
by: Stavrou, Nikolas, et al.
Published: (2026)

Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities
by: Akhound-Sadegh, Tara, et al.
Published: (2025)

Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagation
by: Havaldar, Shreyas, et al.
Published: (2023)

On the Convergence of Overparameterized Problems: Inherent Properties of the Compositional Structure of Neural Networks
by: de Oliveira, Arthur Castello Branco, et al.
Published: (2025)

A Dual-Attention Graph Network for fMRI Data Classification
by: Arbab, Amirali, et al.
Published: (2025)