Nika Haghtalab

Publication Activity (10 Years)

Years Active: 2014-2024
Publications (10 Years): 80

Top Topics

Nash Equilibria

Sample Complexity

Top Venues

Publications

Jessica Dai, Bailey Flanigan, Nika Haghtalab, Meena Jagadeesan, Chara Podimata
Can Probabilistic Feedback Drive User Impacts in Online Platforms? CoRR (2024)
Danny Halawi, Alexander Wei, Eric Wallace, Tony T. Wang, Nika Haghtalab, Jacob Steinhardt
Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation. CoRR (2024)
Nika Haghtalab, Tim Roughgarden, Abhishek Shetty
Smoothed Analysis with Adaptive Adversaries. J. ACM 71 (3) (2024)
Jessica Dai, Bailey Flanigan, Meena Jagadeesan, Nika Haghtalab, Chara Podimata
Can Probabilistic Feedback Drive User Impacts in Online Platforms? AISTATS (2024)
Nika Haghtalab, Mingda Qiao, Kunhe Yang, Eric Zhao
Truthfulness of Calibration Measures. CoRR (2024)
Nika Haghtalab, Mingda Qiao, Kunhe Yang
Platforms for Efficient and Incentive-Aware Collaboration. CoRR (2024)
Nivasini Ananthakrishnan, Stephen Bates, Michael I. Jordan, Nika Haghtalab
Delegating Data Collection in Decentralized Machine Learning. AISTATS (2024)
Constantinos Daskalakis, Noah Golowich, Nika Haghtalab, Abhishek Shetty
Smooth Nash Equilibria: Algorithms and Complexity. ITCS (2024)
Nika Haghtalab, Nicole Immorlica, Brendan Lucier, Markus Mobius, Divyarthi Mohan
Communicating with Anecdotes (Extended Abstract). ITCS (2024)
Alexander Wei, Nika Haghtalab, Jacob Steinhardt
Jailbroken: How Does LLM Safety Training Fail? NeurIPS (2023)
Pranjal Awasthi, Nika Haghtalab, Eric Zhao
Open Problem: The Sample Complexity of Multi-Distribution Learning for VC Classes. COLT (2023)
Nika Haghtalab, Michael I. Jordan, Eric Zhao
A Unifying Perspective on Multi-Calibration: Game Dynamics for Multi-Objective Learning. NeurIPS (2023)
Mahsa Derakhshan, Naveen Durvasula, Nika Haghtalab
Stochastic Minimum Vertex Cover in General Graphs: A 3/2-Approximation. STOC (2023)
Naveen Durvasula, Nika Haghtalab, Manolis Zampetakis
Smoothed Analysis of Online Non-parametric Auctions. EC (2023)
Constantinos Daskalakis, Noah Golowich, Nika Haghtalab, Abhishek Shetty
Smooth Nash Equilibria: Algorithms and Complexity. CoRR (2023)
Nika Haghtalab, Chara Podimata, Kunhe Yang
Calibrated Stackelberg Games: Learning Optimal Commitments Against Calibrated Agents. NeurIPS (2023)
Nivasini Ananthakrishnan, Stephen Bates, Michael I. Jordan, Nika Haghtalab
Delegating Data Collection in Decentralized Machine Learning. CoRR (2023)
Alankrita Bhatt, Nika Haghtalab, Abhishek Shetty
Smoothed Analysis of Sequential Probability Assignment. CoRR (2023)
Meena Jagadeesan, Michael I. Jordan, Nika Haghtalab
Competition, Alignment, and Equilibria in Digital Marketplaces. AAAI (2023)
Alankrita Bhatt, Nika Haghtalab, Abhishek Shetty
Smoothed Analysis of Sequential Probability Assignment. NeurIPS (2023)
Wenshuo Guo, Nika Haghtalab, Kirthevasan Kandasamy, Ellen Vitercik
Leveraging Reviews: Learning to Price with Buyer and Seller Uncertainty. EC (2023)
Pranjal Awasthi, Nika Haghtalab, Eric Zhao
The Sample Complexity of Multi-Distribution Learning for VC Classes. CoRR (2023)
Nika Haghtalab, Chara Podimata, Kunhe Yang
Calibrated Stackelberg Games: Learning Optimal Commitments Against Calibrated Agents. CoRR (2023)
Nika Haghtalab, Michael I. Jordan, Eric Zhao
A Unifying Perspective on Multi-Calibration: Unleashing Game Dynamics for Multi-Objective Learning. CoRR (2023)
Alexander Wei, Nika Haghtalab, Jacob Steinhardt
Jailbroken: How Does LLM Safety Training Fail? CoRR (2023)
Meena Jagadeesan, Michael I. Jordan, Jacob Steinhardt, Nika Haghtalab
Improved Bayes Risk Can Yield Reduced Social Welfare Under Competition. CoRR (2023)
Wenshuo Guo, Nika Haghtalab, Kirthevasan Kandasamy, Ellen Vitercik
Leveraging Reviews: Learning to Price with Buyer and Seller Uncertainty. CoRR (2023)
Mahsa Derakhshan, Naveen Durvasula, Nika Haghtalab
Stochastic Minimum Vertex Cover in General Graphs: a 3/2-Approximation. CoRR (2023)
Meena Jagadeesan, Michael I. Jordan, Jacob Steinhardt, Nika Haghtalab
Improved Bayes Risk Can Yield Reduced Social Welfare Under Competition. NeurIPS (2023)
Nika Haghtalab, Michael I. Jordan, Eric Zhao
On-Demand Sampling: Learning Optimally from Multiple Distributions. NeurIPS (2022)
Meena Jagadeesan, Michael I. Jordan, Nika Haghtalab
Competition, Alignment, and Equilibria in Digital Marketplaces. CoRR (2022)
Nika Haghtalab, Thodoris Lykouris, Sloan Nietert, Alex Wei
Learning in Stackelberg Games with Non-myopic Agents. CoRR (2022)
Nika Haghtalab, Yanjun Han, Abhishek Shetty, Kunhe Yang
Oracle-Efficient Online Learning for Smoothed Adversaries. NeurIPS (2022)
Nika Haghtalab, Nicole Immorlica, Brendan Lucier, Markus Mobius, Divyarthi Mohan
Communicating with Anecdotes. CoRR (2022)
Nika Haghtalab, Michael I. Jordan, Eric Zhao
On-Demand Sampling: Learning Optimally from Multiple Distributions. CoRR (2022)
Nika Haghtalab, Thodoris Lykouris, Sloan Nietert, Alexander Wei
Learning in Stackelberg Games with Non-myopic Agents. EC (2022)
Nika Haghtalab, Tim Roughgarden, Abhishek Shetty
Smoothed Analysis with Adaptive Adversaries. FOCS (2022)
Nika Haghtalab, Yanjun Han, Abhishek Shetty, Kunhe Yang
Oracle-Efficient Online Learning for Beyond Worst-Case Adversaries. CoRR (2022)
Avrim Blum, Nika Haghtalab, Richard Lanas Phillips, Han Shao
One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning. CoRR (2021)
Nika Haghtalab, Tim Roughgarden, Abhishek Shetty
Smoothed Analysis with Adaptive Adversaries. CoRR (2021)
Nika Haghtalab, Matthew O. Jackson, Ariel D. Procaccia
Belief polarization in a complex world: A learning theory perspective. Proc. Natl. Acad. Sci. USA 118 (19) (2021)
Avrim Blum, Nika Haghtalab, Richard Lanas Phillips, Han Shao
One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning. ICML (2021)
Alfredo Torrico, Mohit Singh, Sebastian Pokutta, Nika Haghtalab, Joseph (Seffi) Naor, Nima Anari
Structured Robust Submodular Maximization: Offline and Online Algorithms. INFORMS J. Comput. 33 (4) (2021)
Nika Haghtalab, Tim Roughgarden, Abhishek Shetty
Smoothed Analysis with Adaptive Adversaries. FOCS (2021)
Nika Haghtalab, Nicole Immorlica, Brendan Lucier, Jack Z. Wang
Maximizing Welfare with Incentive-Aware Evaluation Mechanisms. IJCAI (2020)
Miroslav Dudíte, Nika Haghtalab, Haipeng Luo, Robert E. Schapire, Vasilis Syrgkanis, Jennifer Wortman Vaughan
Oracle-efficient Online Learning and Auction Design. J. ACM 67 (5) (2020)
Avrim Blum, John P. Dickerson, Nika Haghtalab, Ariel D. Procaccia, Tuomas Sandholm, Ankit Sharma
Ignorance Is Almost Bliss: Near-Optimal Stochastic Matching with Few Queries. Oper. Res. 68 (1) (2020)
Maria-Florina Balcan, Nika Haghtalab, Colin White
-center Clustering under Perturbation Resilience. ACM Trans. Algorithms 16 (2) (2020)
Lydia T. Liu, Ashia Wilson, Nika Haghtalab, Adam Tauman Kalai, Christian Borgs, Jennifer T. Chayes
The disparate equilibria of algorithmic decision making when individuals invest rationally. FAT* (2020)
Nika Haghtalab, Nicole Immorlica, Brendan Lucier, Jack Z. Wang
Maximizing Welfare with Incentive-Aware Evaluation Mechanisms. CoRR (2020)
Nika Haghtalab, Tim Roughgarden, Abhishek Shetty
Smoothed Analysis of Online and Differentially Private Learning. CoRR (2020)
Maria-Florina Balcan, Nika Haghtalab
Noise in Classification. CoRR (2020)
Nika Haghtalab, Tim Roughgarden, Abhishek Shetty
Smoothed Analysis of Online and Differentially Private Learning. NeurIPS (2020)
Lydia T. Liu, Ashia Wilson, Nika Haghtalab, Adam Tauman Kalai, Christian Borgs, Jennifer T. Chayes
The Disparate Equilibria of Algorithmic Decision Making when Individuals Invest Rationally. CoRR (2019)
Avrim Blum, Nika Haghtalab, MohammadTaghi Hajiaghayi, Saeed Seddighin
Computing Stackelberg Equilibria of Large General-Sum Games. SAGT (2019)
Avrim Blum, Nika Haghtalab, MohammadTaghi Hajiaghayi, Saeed Seddighin
Computing Stackelberg Equilibria of Large General-Sum Games. CoRR (2019)
Nima Anari, Nika Haghtalab, Seffi Naor, Sebastian Pokutta, Mohit Singh, Alfredo Torrico
Structured Robust Submodular Maximization: Offline and Online Algorithms. AISTATS (2019)
Christian Borgs, Jennifer T. Chayes, Nika Haghtalab, Adam Tauman Kalai, Ellen Vitercik
Algorithmic Greenlining: An Approach to Increase Diversity. AIES (2019)
Nika Haghtalab, Cameron Musco, Bo Waggoner
Toward a Characterization of Loss Functions for Distribution Learning. CoRR (2019)
Nika Haghtalab, Simon Mackenzie, Ariel D. Procaccia, Oren Salzman, Siddhartha S. Srinivasa
The Provable Virtue of Laziness in Motion Planning. IJCAI (2019)
Nika Haghtalab, Cameron Musco, Bo Waggoner
Toward a Characterization of Loss Functions for Distribution Learning. NeurIPS (2019)
Avrim Blum, Nika Haghtalab
Algorithms for Generalized Topic Modeling. AAAI (2018)
Nika Haghtalab, Simon Mackenzie, Ariel D. Procaccia, Oren Salzman, Siddhartha S. Srinivasa
The Provable Virtue of Laziness in Motion Planning. ICAPS (2018)
Nika Haghtalab, Ritesh Noothigattu, Ariel D. Procaccia
Weighted Voting Via No-Regret Learning. AAAI (2018)
Avrim Blum, Nika Haghtalab, Ariel D. Procaccia, Mingda Qiao
Collaborative PAC Learning. NIPS (2017)
Nika Haghtalab, Ritesh Noothigattu, Ariel D. Procaccia
Weighted Voting Via No-Regret Learning. CoRR (2017)
Pranjal Awasthi, Avrim Blum, Nika Haghtalab, Yishay Mansour
Efficient PAC Learning from the Crowd. COLT (2017)
Ofer Dekel, Arthur Flajolet, Nika Haghtalab, Patrick Jaillet
Online Learning with a Hint. NIPS (2017)
Nika Haghtalab, Simon Mackenzie, Ariel D. Procaccia, Oren Salzman, Siddhartha S. Srinivasa
The Provable Virtue of Laziness in Motion Planning. CoRR (2017)
Nika Haghtalab, Aron Laszka, Ariel D. Procaccia, Yevgeniy Vorobeychik, Xenofon D. Koutsoukos
Monitoring stealthy diffusion. Knowl. Inf. Syst. 52 (3) (2017)
Avrim Blum, Ioannis Caragiannis, Nika Haghtalab, Ariel D. Procaccia, Eviatar B. Procaccia, Rohit Vaish
Opting Into Optimal Matchings. SODA (2017)
Pranjal Awasthi, Avrim Blum, Nika Haghtalab, Yishay Mansour
Efficient PAC Learning from the Crowd. CoRR (2017)
Miroslav Dudík, Nika Haghtalab, Haipeng Luo, Robert E. Schapire, Vasilis Syrgkanis, Jennifer Wortman Vaughan
Oracle-Efficient Online Learning and Auction Design. FOCS (2017)
Nima Anari, Nika Haghtalab, Joseph Naor, Sebastian Pokutta, Mohit Singh, Alfredo Torrico
Robust Submodular Maximization: Offline and Online Algorithms. CoRR (2017)
Maria-Florina Balcan, Nika Haghtalab, Colin White
k-Center Clustering Under Perturbation Resilience. ICALP (2016)
Pranjal Awasthi, Maria-Florina Balcan, Nika Haghtalab, Hongyang Zhang
Learning and 1-bit Compressed Sensing under Asymmetric Noise. COLT (2016)
Miroslav Dudík, Nika Haghtalab, Haipeng Luo, Robert E. Schapire, Vasilis Syrgkanis, Jennifer Wortman Vaughan
Oracle-Efficient Learning and Auction Design. CoRR (2016)
Avrim Blum, Nika Haghtalab
Generalized Topic Modeling. CoRR (2016)
Nika Haghtalab, Fei Fang, Thanh Hong Nguyen, Arunesh Sinha, Ariel D. Procaccia, Milind Tambe
Three Strategies to Success: Learning Adversary Models in Security Games. IJCAI (2016)
Avrim Blum, Ioannis Caragiannis, Nika Haghtalab, Ariel D. Procaccia, Eviatar B. Procaccia, Rohit Vaish
Opting Into Optimal Matchings. CoRR (2016)
Pranjal Awasthi, Maria-Florina Balcan, Nika Haghtalab, Ruth Urner
Efficient Learning of Linear Separators under Bounded Noise. CoRR (2015)
Maria-Florina Balcan, Nika Haghtalab, Colin White
Symmetric and Asymmetric $k$-center Clustering under Stability. CoRR (2015)
Maria-Florina Balcan, Avrim Blum, Nika Haghtalab, Ariel D. Procaccia
Commitment Without Regrets: Online Learning in Stackelberg Security Games. EC (2015)
Nika Haghtalab, Aron Laszka, Ariel D. Procaccia, Yevgeniy Vorobeychik, Xenofon D. Koutsoukos
Monitoring Stealthy Diffusion. ICDM (2015)
Avrim Blum, John P. Dickerson, Nika Haghtalab, Ariel D. Procaccia, Tuomas Sandholm, Ankit Sharma
Ignorance is Almost Bliss: Near-Optimal Stochastic Matching With Few Queries. EC (2015)
Avrim Blum, Nika Haghtalab, Ariel D. Procaccia
Variational Dropout and the Local Reparameterization Trick. NIPS (2015)
Pranjal Awasthi, Maria-Florina Balcan, Nika Haghtalab, Ruth Urner
Efficient Learning of Linear Separators under Bounded Noise. COLT (2015)
Avrim Blum, Nika Haghtalab, Ariel D. Procaccia
Lazy Defenders Are Almost Optimal against Diligent Attackers. AAAI (2014)
Shai Ben-David, Nika Haghtalab
Clustering in the Presence of Background Noise. ICML (2014)
Avrim Blum, Nika Haghtalab, Ariel D. Procaccia
Learning Optimal Commitment to Overcome Insecurity. NIPS (2014)
Avrim Blum, Nika Haghtalab, Ariel D. Procaccia, Ankit Sharma
Ignorance is Almost Bliss: Near-Optimal Stochastic Matching With Few Queries. CoRR (2014)