ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Daniel Soudry

Daniel Soudry

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 4:04 AM AMS

16

papers

292

total citations

papers (16)

The Knowledge Within: Methods for Data-Free Model Compression

Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy

NEURIPS 2020arXiv

Explore to Generalize in Zero-Shot RL

NEURIPS 2023arXiv

Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activations

Physics-Aware Downsampling with Deep Learning for Scalable Flood Modeling

NEURIPS 2021arXiv

How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers

How do Minimum-Norm Shallow Denoisers Look in Function Space?

NEURIPS 2023arXiv

Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators

When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets

DropCompute: simple and more robust distributed synchronous training via compute variance reduction

NEURIPS 2023arXiv

Optimal Rates in Continual Linear Regression via Increasing Regularization

NEURIPS 2025arXiv

Are Greedy Task Orderings Better Than Random in Continual Linear Regression?

NEURIPS 2025arXiv

Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks

Alias-Free ViT: Fractional Shift Invariance via Linear Attention

NEURIPS 2025arXiv

The Implicit Bias of Minima Stability: A View from Function Space

Augment Your Batch: Improving Generalization Through Instance Repetition