Roman Novak
13 papers · 2018–2024 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Conference Polyglot (3) π Academic Marathon (6) π Interdisciplinary Bridge π§ Keyword Pioneer π Cross-Pollinator (13)
πΊοΈ
Taxonomy Completionist
(19)
π
Interdisciplinary Bridge
π§
Keyword Pioneer
π
Triple Crown
π€
Dynamic Duo
(11)
π
Conference Pioneer
π₯
Unstoppable
(5)
π
Century Club
(13)
Conferences
ICLR (5)
ICML (4)
NIPS (4)
Top co-authors
Keywords
neural tangent kernel
(4)
neural network gaussian process
(3)
infinite width limit
(2)
kernel methods
(2)
kl divergence
(1)
posterior sampling
(1)
neural network optimization
(1)
markov chain monte carlo
(1)
gaussian process
(1)
gradient descent
(1)
matrix computation
(1)
convolutional neural network
(1)
weight decay
(1)
dataset distillation
(1)
positional encoding
(1)
bayesian neural network
(1)
convolutional kernel
(1)
linear model
(1)
infinite width
(1)
network initialization
(1)
Papers
Small-scale proxies for large-scale Transformer training instabilities
ICLR 2024
Scaling Exponents Across Parameterizations and Optimizers
ICML 2024
Fast Finite Width Neural Tangent Kernel
ICML 2022
Fast Neural Kernel Embeddings for General Activations
NIPS 2022
Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling
ICML 2022
Dataset Distillation with Infinitely Wide Convolutional Networks
NIPS 2021
Finite Versus Infinite Neural Networks: an Empirical Study
NIPS 2020
Neural Tangents: Fast and Easy Infinite Neural Networks in Python
ICLR 2020
Infinite attention: NNGP and NTK for deep attention networks
ICML 2020
Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes
ICLR 2019
Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
NIPS 2019
Sensitivity and Generalization in Neural Networks: an Empirical Study
ICLR 2018
Deep Neural Networks as Gaussian Processes
ICLR 2018