Maxim Rakhuba
11 papers · 2020–2026 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π§ Keyword Pioneer π Cross-Pollinator (8) πΊοΈ Taxonomy Completionist (24) π Interdisciplinary Bridge
π
Conference Polyglot
(7)
π
Academic Marathon
(5)
π§¬
Topic Evolution
π
Century Club
(10)
ποΈ
Keyword Collector
(55)
Conferences
AISTATS (3)
NIPS (2)
AAAI (1)
ACL (1)
COLT (1)
ECCV (1)
ICCV (1)
ICML (1)
Top co-authors
Keywords
tensor decomposition
(3)
model compression
(3)
neural network compression
(3)
parameter reduction
(2)
structured matrix
(2)
parameter efficiency
(2)
weight matrix
(2)
singular value decomposition
(1)
covariance estimation
(1)
adversarial robustness
(1)
knowledge distillation
(1)
high-dimensional statistics
(1)
model calibration
(1)
matrix decomposition
(1)
tensor factorization
(1)
matrix factorization
(1)
differentiable programming
(1)
kronecker product
(1)
matrix estimation
(1)
manifold structure
(1)
Papers
Matrix-Free Two-to-Infinity and One-to-Two Norms Estimation
AAAI 2026
ProcrustesGPT: Compressing LLMs with Structured Matrices and Orthogonal Transformations
ACL 2025
Knowledge Graph Completion with Mixed Geometry Tensor Factorization
AISTATS 2025
Group and Shuffle: Efficient Structured Orthogonal Parametrization
NIPS 2024
Training a Tucker Model With Shared Factors: a Riemannian Optimization Approach
AISTATS 2024
Dimension-free Structured Covariance Estimation
COLT 2024
Tight and Efficient Upper Bound on Spectral Norm of Convolutional Layers
ECCV 2024
Towards Practical Control of Singular Values of Convolutional Layers
NIPS 2022
Spectral Tensor Train Parameterization of Deep Learning Layers
AISTATS 2021
Cherry-Picking Gradients: Learning Low-Rank Embeddings of Visual Data via Differentiable Cross-Approximation
ICCV 2021
T-Basis: a Compact Representation for Neural Networks
ICML 2020