Valerii Likhosherstov
17 papers · 2019–2024 · 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 ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (27) π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π
Triple Crown
π
Grand Slam
π€
Dynamic Duo
(14)
π
Keyword Champion
(4)
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
ποΈ
Keyword Collector
(75)
β‘
Prolific Year Β· Productive
Top co-authors
Research topics
Machine Learning
(14)
Deep Learning
(11)
Architectures
(10)
Optimization & Theory Β· Machine Learning
(9)
Mathematics & Optimization
(6)
Core Methods
(6)
Optimization & Theory Β· Deep Learning
(4)
Techniques
(4)
Artificial Intelligence
(3)
Mathematics
(3)
Optimization
(3)
Application Areas
(2)
Core AI
(2)
Natural Language Processing
(1)
Reinforcement Learning
(1)
Keywords
gaussian kernel
(4)
kernel approximation
(4)
softmax kernel
(4)
random feature
(4)
transformer architecture
(3)
graph theory
(3)
linear attention
(3)
stochastic gradient descent
(2)
attention mechanism
(2)
spectral analysis
(2)
orthogonal group
(2)
ising model
(1)
theoretical analysis
(1)
model architecture
(1)
matrix factorization
(1)
point cloud
(1)
variance reduction
(1)
language modeling
(1)
self-attention mechanism
(1)
fast multipole method
(1)
Papers
Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers
AISTATS 2024
Scalable Neural Network Kernels
ICLR 2024
Adaptive Computation with Elastic Input Sequence
ICML 2023
Dense-Exponential Random Features: Sharp Positive Estimators of the Gaussian Kernel
NeurIPS 2023
Efficient Graph Field Integrators Meet Point Clouds
ICML 2023
On the Expressive Flexibility of Self-Attention Matrices
AAAI 2023
Simplex Random Features
ICML 2023
Chefs' Random Tables: Non-Trigonometric Random Features
NeurIPS 2022
From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformers
ICML 2022
Hybrid Random Features
ICLR 2022
CWY Parametrization: a Solution for Parallelized Optimization of Orthogonal and Stiefel Matrices
AISTATS 2021
Debiasing a First-order Heuristic for Approximate Bi-level Optimization
ICML 2021
Rethinking Attention with Performers
ICLR 2021
Sub-Linear Memory: How to Make Performers SLiM
NeurIPS 2021
Ode to an ODE
NeurIPS 2020
Stochastic Flows and Geometric Optimization on the Orthogonal Group
ICML 2020
Inference and Sampling of K_33-free Ising Models
ICML 2019