Konstantin Donhauser
13 papers · 2021–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (14) π§ Keyword Pioneer π Conference Polyglot (6) π£ Hot Topic Early Bird π Cross-Pollinator (8)
π
Interdisciplinary Bridge
π€
Dynamic Duo
(11)
β‘
Prolific Year
(5)
π₯
Unstoppable
(5)
π
Century Club
(13)
Conferences
ICML (5)
AISTATS (3)
ICLR (2)
ALT (1)
NIPS (1)
UAI (1)
Top co-authors
Research topics
Keywords
causal inference
(1)
minimax optimality
(1)
l1 regularization
(1)
sparse regression
(1)
generalization error
(1)
high-dimensional regression
(1)
high-dimensional analysis
(1)
kernel ridge regression
(1)
eigenvalue decay
(1)
private data release
(1)
support vector machine
(1)
generalization bound
(1)
inductive bia
(1)
high dimensional
(1)
lower bound
(1)
synthetic datum
(1)
benign overfitting
(1)
prediction error
(1)
randomized trial
(1)
differential privacy
(1)
Papers
ViTally Consistent: Scaling Biological Representation Learning for Cell Microscopy
ICML 2025
Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models
ICML 2025
Copyright-Protected Language Generation via Adaptive Model Fusion
ICLR 2025
Tight bounds for maximum $\ell_1$-margin classifiers
ALT 2024
Detecting critical treatment effect bias in small subgroups
UAI 2024
Hidden yet quantifiable: A lower bound for confounding strength using randomized trials
AISTATS 2024
Certified private data release for sparse Lipschitz functions
AISTATS 2024
Privacy-Preserving Data Release Leveraging Optimal Transport and Particle Gradient Descent
ICML 2024
Strong inductive biases provably prevent harmless interpolation
ICLR 2023
Fast rates for noisy interpolation require rethinking the effect of inductive bias
ICML 2022
Tight bounds for minimum $\ell_1$-norm interpolation of noisy data
AISTATS 2022
Interpolation can hurt robust generalization even when there is no noise
NIPS 2021
How rotational invariance of common kernels prevents generalization in high dimensions
ICML 2021