James Martens
16 papers · 2010–2024 · 5 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 ↓+6 more ↓ Show less ↑
🗺️ Taxonomy Completionist (24) 🏃 Academic Marathon · Half 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird
🏆
Keyword Champion
(3)
🧭
Keyword Pioneer
🗃️
Keyword Collector
(64)
💎
Century Club · Bronze
❓
The Questioner
🚀
Conference Pioneer
Top co-authors
Research topics
Machine Learning
(14)
Optimization & Theory · Machine Learning
(13)
Deep Learning
(9)
Architectures
(4)
Learning Types
(4)
Artificial Intelligence
(3)
Techniques
(3)
Bayesian & Probabilistic · Artificial Intelligence
(2)
Bayesian & Probabilistic · Machine Learning
(2)
Models
(2)
Optimization & Theory · Deep Learning
(2)
Mathematics & Optimization
(1)
Reinforcement Learning
(1)
Core AI
(1)
Core Methods
(1)
Keywords
second-order optimization
(4)
natural gradient
(4)
neural network optimization
(3)
stochastic gradient descent
(3)
fisher information matrix
(3)
kronecker factorization
(3)
convergence analysis
(3)
curvature approximation
(2)
hamiltonian game
(2)
restricted boltzmann machine
(2)
generative adversarial network
(2)
neural network
(2)
differentiable game
(2)
recurrent neural network
(2)
gradient descent
(2)
deep neural network
(2)
symplectic gradient adjustment
(2)
nash equilibrium
(1)
probabilistic inference
(1)
markov chain monte carlo
(1)
Papers
Normalization and effective learning rates in reinforcement learning
NeurIPS 2024
Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation
ICLR 2023
Pre-training via Denoising for Molecular Property Prediction
ICLR 2023
Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers
ICLR 2022
New Insights and Perspectives on the Natural Gradient Method
JMLR 2020
Adversarial Robustness through Local Linearization
NeurIPS 2019
Differentiable Game Mechanics
JMLR 2019
Fast Convergence of Natural Gradient Descent for Over-Parameterized Neural Networks
NeurIPS 2019
Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model
NeurIPS 2019
Kronecker-factored Curvature Approximations for Recurrent Neural Networks
ICLR 2018
The Mechanics of n-Player Differentiable Games
ICML 2018
A Kronecker-factored approximate Fisher matrix for convolution layers
ICML 2016
Optimizing Neural Networks with Kronecker-factored Approximate Curvature
ICML 2015
On the importance of initialization and momentum in deep learning
ICML 2013
On the Representational Efficiency of Restricted Boltzmann Machines
NeurIPS 2013
Parallelizable Sampling of Markov Random Fields
AISTATS 2010