Dmitry Kobak
7 papers · 2020–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
๐งญ Keyword Pioneer ๐ Conference Polyglot (4) ๐ Academic Marathon (5) ๐ Cross-Pollinator (8) ๐ Interdisciplinary Bridge
๐ฃ
Hot Topic Early Bird
Conferences
ICLR (2)
ICML (2)
JMLR (2)
NIPS (1)
Top co-authors
Keywords
statistical learning
(1)
dimensionality reduction
(1)
manifold learning
(1)
cluster analysis
(1)
ridge regression
(1)
data visualization
(1)
topological data analysis
(1)
linear regression
(1)
persistent homology
(1)
high-dimensional datum
(1)
spectral method
(1)
implicit regularization
(1)
ridge regularization
(1)
minimum-norm estimator
(1)
underdetermined system
(1)
neighbor embedding
(1)
effective resistance
(1)
diffusion distance
(1)
Papers
On the Importance of Embedding Norms in Self-Supervised Learning
ICML 2025
Scaling Down Deep Learning with MNIST-1D
ICML 2024
Persistent Homology for High-dimensional Data Based on Spectral Methods
NIPS 2024
Unsupervised visualization of image datasets using contrastive learning
ICLR 2023
From $t$-SNE to UMAP with contrastive learning
ICLR 2023
Attraction-Repulsion Spectrum in Neighbor Embeddings
JMLR 2022
The Optimal Ridge Penalty for Real-world High-dimensional Data Can Be Zero or Negative due to the Implicit Ridge Regularization
JMLR 2020