Dmitry Kobak
7 papers · 2020–2025 · 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 ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(17)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Machine Learning
(5)
Deep Learning
(3)
Core Methods
(3)
Learning Types · Deep Learning
(3)
Optimization & Theory
(3)
Learning Types · Machine Learning
(2)
Computer Vision
(1)
Data Science & Analytics
(1)
Mathematics & Optimization
(1)
Analysis
(1)
Application Areas
(1)
Applications
(1)
Mathematics
(1)
Techniques
(1)
Keywords
dimensionality reduction
(3)
neighbor embedding
(2)
contrastive learning
(2)
self-supervised learning
(1)
ridge regression
(1)
data visualization
(1)
topological data analysis
(1)
linear regression
(1)
persistent homology
(1)
convergence rate
(1)
high-dimensional data
(1)
spectral method
(1)
implicit regularization
(1)
ridge regularization
(1)
cosine similarity
(1)
negative sampling
(1)
minimum-norm estimator
(1)
underdetermined system
(1)
nearest neighbor graph
(1)
lottery ticket
(1)
Papers
On the Importance of Embedding Norms in Self-Supervised Learning
ICML 2025
Persistent Homology for High-dimensional Data Based on Spectral Methods
NeurIPS 2024
Scaling Down Deep Learning with MNIST-1D
ICML 2024
From t-SNE to UMAP with contrastive learning
ICLR 2023
Unsupervised visualization of image datasets using 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