Picture for Natalia Ponomareva

Natalia Ponomareva

An Optimization Framework for Differentially Private Sparse Fine-Tuning

Add code
Mar 17, 2025
Viaarxiv icon

HASSLE-free: A unified Framework for Sparse plus Low-Rank Matrix Decomposition for LLMs

Add code
Feb 02, 2025
Viaarxiv icon

Private prediction for large-scale synthetic text generation

Add code
Jul 16, 2024
Viaarxiv icon

DART: A Principled Approach to Adversarially Robust Unsupervised Domain Adaptation

Add code
Feb 16, 2024
Viaarxiv icon

JetTrain: IDE-Native Machine Learning Experiments

Add code
Feb 16, 2024
Viaarxiv icon

Scaling Laws for Downstream Task Performance of Large Language Models

Add code
Feb 06, 2024
Figure 1 for Scaling Laws for Downstream Task Performance of Large Language Models
Figure 2 for Scaling Laws for Downstream Task Performance of Large Language Models
Figure 3 for Scaling Laws for Downstream Task Performance of Large Language Models
Figure 4 for Scaling Laws for Downstream Task Performance of Large Language Models
Viaarxiv icon

Explaining and Adapting Graph Conditional Shift

Add code
Jun 05, 2023
Figure 1 for Explaining and Adapting Graph Conditional Shift
Figure 2 for Explaining and Adapting Graph Conditional Shift
Figure 3 for Explaining and Adapting Graph Conditional Shift
Figure 4 for Explaining and Adapting Graph Conditional Shift
Viaarxiv icon

COMET: Learning Cardinality Constrained Mixture of Experts with Trees and Local Search

Add code
Jun 05, 2023
Viaarxiv icon

Harnessing large-language models to generate private synthetic text

Add code
Jun 02, 2023
Figure 1 for Harnessing large-language models to generate private synthetic text
Figure 2 for Harnessing large-language models to generate private synthetic text
Figure 3 for Harnessing large-language models to generate private synthetic text
Figure 4 for Harnessing large-language models to generate private synthetic text
Viaarxiv icon

Privacy-Preserving Recommender Systems with Synthetic Query Generation using Differentially Private Large Language Models

Add code
May 10, 2023
Figure 1 for Privacy-Preserving Recommender Systems with Synthetic Query Generation using Differentially Private Large Language Models
Figure 2 for Privacy-Preserving Recommender Systems with Synthetic Query Generation using Differentially Private Large Language Models
Figure 3 for Privacy-Preserving Recommender Systems with Synthetic Query Generation using Differentially Private Large Language Models
Figure 4 for Privacy-Preserving Recommender Systems with Synthetic Query Generation using Differentially Private Large Language Models
Viaarxiv icon