NP
Natalia Ponomareva
cs.LGstat.MLcs.CRcs.CLcs.CVcs.AIcs.IRcs.ROcs.SEmath.OC
On Valency
published · living versionsW_4amt7tv3·v1 · currentpublished
SimHack: Predicting the onset of detectable reward hacking before RL training
with Junwei Deng, Alex Bie
1 version
Preprints & journals
27 papers in the corpus · 2017–2026SimHack: Predicting the onset of detectable reward hacking before RL training2610.28707v1 · Junwei Deng, Alex Bie, Natalia Ponomareva2026 · 0 citationsarXivon Valency
Two For The Price Of One: Curvature-Aware Pruning Preserves Influence Functions Too2610.18516v1 · Mehdi Makni, Natalia Ponomareva, Rahul Mazumder2026 · 0 citationsarXiv
ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?2606.01849v2 · Peihan Liu, Lucas Rosenblatt, Weiwei Kong et al.2026 · 0 citationsarXiv
Decomposing Private Image Generation via Coarse-to-Fine Wavelet Modeling2602.23262v1 · Jasmine Bayrooti, Weiwei Kong, Natalia Ponomareva et al.2026 · 0 citationsarXiv
Privately Fine-Tuned LLMs Preserve Temporal Dynamics in Tabular Data2602.02766v1 · Lucas Rosenblatt, Peihan Liu, Ryan McKenna et al.2026 · 0 citationsarXiv
How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy2512.03238v2 · Natalia Ponomareva, Zheng Xu, H. Brendan McMahan et al.2025 · 1 citationJAIR 2026, vol. 86 JAIR, Vol. 86
An Optimization Framework for Differentially Private Sparse Fine-Tuning2503.12822v1 · Mehdi Makni, Kayhan Behdin, Gabriel Afriat et al.2025 · 0 citationsarXiv
HASSLE-free: A unified Framework for Sparse plus Low-Rank Matrix Decomposition for LLMs2502.00899v1 · Mehdi Makni, Kayhan Behdin, Zheng Xu et al.2025 · 0 citationsarXiv
Private prediction for large-scale synthetic text generation2407.12108v2 · Kareem Amin, Alex Bie, Weiwei Kong et al.2024 · 5 citationsarXiv
OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization2403.12983v1 · Xiang Meng, Shibal Ibrahim, Kayhan Behdin et al.2024 · 2 citationsarXiv
JetTrain: IDE-Native Machine Learning Experiments2402.10857v1 · Artem Trofimov, Mikhail Kostyukov, Sergei Ugdyzhekov et al.2024 · 0 citationsarXiv
DART: A Principled Approach to Adversarially Robust Unsupervised Domain Adaptation2402.11120v1 · Yunjuan Wang, Hussein Hazimeh, Natalia Ponomareva et al.2024 · 2 citationsarXiv
Scaling Laws for Downstream Task Performance of Large Language Models2402.04177v3 · Berivan Isik, Natalia Ponomareva, Hussein Hazimeh et al.2024 · 3 citationsarXiv
COMET: Learning Cardinality Constrained Mixture of Experts with Trees and Local Search2306.02824v1 · Shibal Ibrahim, Wenyu Chen, Hussein Hazimeh et al.2023 · 2 citationsarXiv
Explaining and Adapting Graph Conditional Shift2306.03256v1 · Qi Zhu, Yizhu Jiao, Natalia Ponomareva et al.2023 · 2 citationsarXiv
Harnessing large-language models to generate private synthetic text2306.01684v2 · Alexey Kurakin, Natalia Ponomareva, Umar Syed et al.2023 · 3 citationsarXiv
Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language Models2305.05973v3 · Aldo Gael Carranza, Rezsa Farahani, Natalia Ponomareva et al.2023 · 9 citationsarXiv
How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy2303.00654v3 · Natalia Ponomareva, Hussein Hazimeh, Alex Kurakin et al.2023 · 166 citationsJournal of Artificial Intelligence Research 77 (2023) 1113-1201
Fast as CHITA: Neural Network Pruning with Combinatorial Optimization2302.14623v1 · Riade Benbaki, Wenyu Chen, Xiang Meng et al.2023 · 6 citationsarXiv
Mind the (optimality) Gap: A Gap-Aware Learning Rate Scheduler for Adversarial Nets2302.00089v1 · Hussein Hazimeh, Natalia Ponomareva2023 · 0 citationsarXiv
Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance2110.06893v3 · Shibal Ibrahim, Natalia Ponomareva, Rahul Mazumder2021 · 13 citationsarXiv
Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data2108.01099v2 · Qi Zhu, Natalia Ponomareva, Jiawei Han et al.2021 · 45 citationsarXiv
The Tree Ensemble Layer: Differentiability meets Conditional Computation2002.07772v2 · Hussein Hazimeh, Natalia Ponomareva, Petros Mol et al.2020 · 33 citationsarXiv
Agent Prioritization for Autonomous Navigation1909.08792v1 · Khaled S. Refaat, Kai Ding, Natalia Ponomareva et al.2019 · 18 citationsarXiv
Accelerating Gradient Boosting Machine1903.08708v3 · Haihao Lu, Sai Praneeth Karimireddy, Natalia Ponomareva et al.2019 · 12 citationsarXiv
Compact Multi-Class Boosted Trees1710.11547v1 · Natalia Ponomareva, Thomas Colthurst, Gilbert Hendry et al.2017 · 22 citationsarXiv
TF Boosted Trees: A scalable TensorFlow based framework for gradient boosting1710.11555v1 · Natalia Ponomareva, Soroush Radpour, Gilbert Hendry et al.2017 · 24 citationsarXiv
Career total: 50 works. 27 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.