← Authors

Gintare Karolina Dziugaite

28 papers · 2018–2025 · 6 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (11) πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (6) πŸ—ΊοΈ Taxonomy Completionist (35) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird πŸƒ Academic Marathon (7) πŸ† Keyword Champion (3) 🀝 Dynamic Duo (11) πŸ—ƒοΈ Keyword Collector (72) ❓ The Questioner (2) ⚑ Prolific Year (5) πŸ’Ž Century Club (28) πŸ”₯ Unstoppable (8) πŸ“ˆ Trend Setter

Conferences

NIPS (9) ICML (7) AISTATS (5) ICLR (5) ALT (1) COLT (1)

Top co-authors

Daniel M. Roy (11) Mahdi Haghifam (6) Daniel Roy (5) Jonathan Frankle (5) Michael Carbin (4) Surya Ganguli (4) Mansheej Paul (4) Jeffrey Negrea (3) Tian Jin (3) Nazanin Mohammadi Sepahvand (2)

Research topics

Probability (1)

Keywords

generalization bound (8) pac-bayes bound (4) stochastic gradient langevin dynamics (3) generalization error (2) iterative magnitude pruning (2) loss landscape (2) training dynamics (2) prior distribution (2) mutual information (2) conditional mutual information (2) lottery ticket hypothesis (2) information-theoretic bound (2) sparse training (2) differential privacy (2) posterior distribution (2) stochastic gradient descent (2) neural network pruning (2) kernel learning (1) deep learning (1) sample complexity (1)

Papers

The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws ICLR 2025
Selective Unlearning via Representation Erasure Using Domain Adversarial Training ICLR 2025
Leveraging Per-Instance Privacy for Machine Unlearning ICML 2025
The Size of Teachers as a Measure of Data Complexity: PAC-Bayes Excess Risk Bounds and Scaling Laws AISTATS 2025
Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization ICML 2025
Information Complexity of Stochastic Convex Optimization: Applications to Generalization, Memorization, and Tracing ICML 2024
Mixtures of Experts Unlock Parameter Scaling for Deep RL ICML 2024
Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias AISTATS 2024
The Cost of Scaling Down Large Language Models: Reducing Model Size Affects Memory before In-context Learning ICLR 2024
Limitations of Information-Theoretic Generalization Bounds for Gradient Descent Methods in Stochastic Convex Optimization ALT 2023
Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask? ICLR 2023
Pruning’s Effect on Generalization Through the Lens of Training and Regularization NIPS 2022
Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks NIPS 2022
On the Role of Data in PAC-Bayes Bounds AISTATS 2021
Information-Theoretic Generalization Bounds for Stochastic Gradient Descent COLT 2021
Pruning Neural Networks at Initialization: Why Are We Missing the Mark? ICLR 2021
Towards a Unified Information-Theoretic Framework for Generalization NIPS 2021
Deep Learning on a Data Diet: Finding Important Examples Early in Training NIPS 2021
RelatIF: Identifying Explanatory Training Samples via Relative Influence AISTATS 2020
Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel NIPS 2020
Stochastic Neural Network with Kronecker Flow AISTATS 2020
In Defense of Uniform Convergence: Generalization via Derandomization with an Application to Interpolating Predictors ICML 2020
In search of robust measures of generalization NIPS 2020
Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms NIPS 2020
Linear Mode Connectivity and the Lottery Ticket Hypothesis ICML 2020
Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates NIPS 2019
Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors ICML 2018
Data-dependent PAC-Bayes priors via differential privacy NIPS 2018