Aleksandar Botev
8 papers · 2017–2023 · 4 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (15) 🐣 Hot Topic Early Bird
🚀
Conference Pioneer
Venues
Top co-authors
Research topics
Keywords
kronecker factorization
(2)
hamiltonian dynamics
(2)
neural network
(2)
laplace approximation
(2)
model evaluation
(1)
image reconstruction
(1)
neural network optimization
(1)
posterior distribution
(1)
importance sampling
(1)
large-scale classification
(1)
kernel shaping
(1)
signal propagation
(1)
second-order optimization
(1)
generative model
(1)
deep neural network
(1)
normalizing flow
(1)
uncertainty estimation
(1)
activation function
(1)
latent dynamics
(1)
parameter initialization
(1)
Papers
Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation
ICLR 2023
Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers
ICLR 2022
SyMetric: Measuring the Quality of Learnt Hamiltonian Dynamics Inferred from Vision
NeurIPS 2021
Hamiltonian Generative Networks
ICLR 2020
A Scalable Laplace Approximation for Neural Networks
ICLR 2018
Online Structured Laplace Approximations for Overcoming Catastrophic Forgetting
NeurIPS 2018
Complementary Sum Sampling for Likelihood Approximation in Large Scale Classification
AISTATS 2017
Practical Gauss-Newton Optimisation for Deep Learning
ICML 2017