Roman Novak
13 papers · 2018–2024 · 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 ↓+9 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (24) π Academic Marathon Β· Sprint π Conference Polyglot Β· Bronze π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π
Triple Crown
π
Keyword Champion
(3)
π§
Keyword Pioneer
π€
Dynamic Duo
(11)
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
π
Conference Pioneer
ποΈ
Keyword Collector
(55)
π
Trend Setter
Venues
Top co-authors
Research topics
Machine Learning
(13)
Optimization & Theory Β· Machine Learning
(12)
Deep Learning
(10)
Architectures
(7)
Artificial Intelligence
(3)
Mathematics & Optimization
(2)
Application Areas
(2)
Bayesian & Probabilistic Β· Artificial Intelligence
(2)
Core Methods
(2)
Models
(2)
Optimization
(2)
Optimization & Theory Β· Deep Learning
(2)
Computer Vision
(1)
Bayesian & Probabilistic Β· Machine Learning
(1)
Core AI
(1)
Keywords
neural tangent kernel
(5)
gaussian process
(3)
bayesian inference
(3)
neural network gaussian process
(3)
gradient descent
(2)
convolutional neural network
(2)
kernel methods
(2)
infinite width
(2)
neural network
(2)
neural network optimization
(2)
infinite-width limit
(2)
data augmentation
(1)
monte carlo estimation
(1)
generalization error
(1)
attention mechanism
(1)
double descent
(1)
relu activation
(1)
markov chain monte carlo
(1)
learning rate
(1)
posterior sampling
(1)
Papers
Scaling Exponents Across Parameterizations and Optimizers
ICML 2024
Small-scale proxies for large-scale Transformer training instabilities
ICLR 2024
Fast Finite Width Neural Tangent Kernel
ICML 2022
Fast Neural Kernel Embeddings for General Activations
NeurIPS 2022
Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling
ICML 2022
Dataset Distillation with Infinitely Wide Convolutional Networks
NeurIPS 2021
Finite Versus Infinite Neural Networks: an Empirical Study
NeurIPS 2020
Infinite attention: NNGP and NTK for deep attention networks
ICML 2020
Neural Tangents: Fast and Easy Infinite Neural Networks in Python
ICLR 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
NeurIPS 2019
Deep Neural Networks as Gaussian Processes
ICLR 2018
Sensitivity and Generalization in Neural Networks: an Empirical Study
ICLR 2018