Andres Potapczynski
10 papers · 2020–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (30) π Academic Marathon Β· Sprint π Conference Polyglot Β· Bronze π Triple Crown
ποΈ
Keyword Collector
(56)
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
Venues
Top co-authors
Research topics
Machine Learning
(10)
Deep Learning
(7)
Application Areas
(6)
Optimization & Theory Β· Machine Learning
(5)
Artificial Intelligence
(4)
Core Methods
(4)
Architectures
(3)
Core AI
(3)
Optimization & Theory Β· Deep Learning
(3)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Bayesian & Probabilistic
(1)
Generation
(1)
Learning Types
(1)
Mathematics
(1)
Keywords
neural network
(4)
structured matrice
(2)
partial differential equation
(2)
gaussian process
(2)
transfer learning
(1)
hyperparameter learning
(1)
neural network compression
(1)
out-of-distribution generalization
(1)
variational inference
(1)
automatic differentiation
(1)
efficient computing
(1)
curse of dimensionality
(1)
conjugate gradient
(1)
numerical linear algebra
(1)
matrix computation
(1)
discrete distribution
(1)
learning rate
(1)
generalization bound
(1)
pac-bayes bound
(1)
neural network optimization
(1)
Papers
Customizing the Inductive Biases of Softmax Attention using Structured Matrices
ICML 2025
Training Flexible Models of Genetic Variant Effects from Functional Annotations using Accelerated Linear Algebra
ICML 2025
Compute Better Spent: Replacing Dense Layers with Structured Matrices
ICML 2024
Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices
NeurIPS 2024
A Stable and Scalable Method for Solving Initial Value PDEs with Neural Networks
ICLR 2023
CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra
NeurIPS 2023
Simple and Fast Group Robustness by Automatic Feature Reweighting
ICML 2023
PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization
NeurIPS 2022
Bias-Free Scalable Gaussian Processes via Randomized Truncations
ICML 2021
Invertible Gaussian Reparameterization: Revisiting the Gumbel-Softmax
NeurIPS 2020