Nika Haghtalab

111 papers A* 42A 5B 2C 1Journal 56Unranked 4

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Subliminal Effects in Your Data: A General Mechanism via Log-Linearity. CoRR Ishaq Aden-Ali, Noah Golowich, Allen Liu, Abhishek Shetty, Ankur Moitra, Nika Haghtalab
2025	A*	`conf`	Conference on Learning Theory 2025: Preface. COLT Nika Haghtalab, Ankur Moitra
2025	J	`jnl`	Diffusion Language Models are Provably Optimal Parallel Samplers. CoRR Haozhe Jiang, Nika Haghtalab, Lijie Chen
2025	J	`jnl`	Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences? CoRR Paul Gölz, Nika Haghtalab, Kunhe Yang
2025	J	`jnl`	From Style to Facts: Mapping the Boundaries of Knowledge Injection with Finetuning. CoRR Eric Zhao, Pranjal Awasthi, Nika Haghtalab
2025	A*	`conf`	Leakage-Robust Bayesian Persuasion. EC Nika Haghtalab, Mingda Qiao, Kunhe Yang
2025	A*	`conf`	Learning With Multi-Group Guarantees For Clusterable Subpopulations. ICML Jessica Dai, Nika Haghtalab, Eric Zhao
2025	J	`jnl`	Multi-Agent Risks from Advanced AI. CoRR Lewis Hammond, Alan Chan, Jesse Clifton, Jason Hoelscher-Obermaier, Akbir Khan, Euan McLean, Chandler Smith, Wolfram Barfuss, Jakob N. Foerster, Tomas Gavenciak, The Anh Han, Edward Hughes, Vojtech Kovarík, Jan Kulveit, Joel Z. Leibo, Caspar Oesterheld, Christian Schröder de Witt, Nisarg Shah, Michael P. Wellman, Paolo Bova, Theodor Cimpeanu, Carson Ezell, Quentin Feuillade-Montixi, Matija Franklin, Esben Kran, Igor Krawczuk, Max Lamparth, Niklas Lauffer, Alexander Meinke, Sumeet Motwani, Anka Reuel, Vincent Conitzer, Michael Dennis, Iason Gabriel, Adam Gleave, Gillian K. Hadfield, Nika Haghtalab, Atoosa Kasirzadeh, Sébastien Krier, Kate Larson, Joel Lehman, David C. Parkes, Georgios Piliouras, Iyad Rahwan
2025	J	`jnl`	On Surjectivity of Neural Networks: Can you elicit any behavior from your model? CoRR Haozhe Jiang, Nika Haghtalab
2025	J	`jnl`	Panprediction: Optimal Predictions for Any Downstream Task and Loss. CoRR Sivaraman Balakrishnan, Nika Haghtalab, Daniel Hsu, Brian Lee, Eric Zhao
2025	A*	`conf`	Platforms for Efficient and Incentive-Aware Collaboration. SODA Nika Haghtalab, Mingda Qiao, Kunhe Yang
2025	J	`jnl`	Sample-Adaptivity Tradeoff in On-Demand Sampling. CoRR Nika Haghtalab, Omar Montasser, Mingda Qiao
2025	A*	`ed.`	The Thirty Eighth Annual Conference on Learning Theory, 30-4 July 2025, Lyon, France. COLT Nika Haghtalab, Ankur Moitra
2024	J	`jnl`	Algorithmic Content Selection and the Impact of User Disengagement. CoRR Emilio Calvano, Nika Haghtalab, Ellen Vitercik, Eric Zhao
2024	A	`conf`	Can Probabilistic Feedback Drive User Impacts in Online Platforms? AISTATS Jessica Dai, Bailey Flanigan, Meena Jagadeesan, Nika Haghtalab, Chara Podimata
2024	J	`jnl`	Can Probabilistic Feedback Drive User Impacts in Online Platforms? CoRR Jessica Dai, Bailey Flanigan, Nika Haghtalab, Meena Jagadeesan, Chara Podimata
2024	A	`conf`	Communicating with Anecdotes (Extended Abstract). ITCS Nika Haghtalab, Nicole Immorlica, Brendan Lucier, Markus Mobius, Divyarthi Mohan
2024	A*	`conf`	Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation. ICML Danny Halawi, Alexander Wei, Eric Wallace, Tony Tong Wang, Nika Haghtalab, Jacob Steinhardt
2024	J	`jnl`	Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation. CoRR Danny Halawi, Alexander Wei, Eric Wallace, Tony T. Wang, Nika Haghtalab, Jacob Steinhardt
2024	A	`conf`	Delegating Data Collection in Decentralized Machine Learning. AISTATS Nivasini Ananthakrishnan, Stephen Bates, Michael I. Jordan, Nika Haghtalab
2024	J	`jnl`	Is Knowledge Power? On the (Im)possibility of Learning from Strategic Interaction. CoRR Nivasini Ananthakrishnan, Nika Haghtalab, Chara Podimata, Kunhe Yang
2024	A*	`conf`	Is Knowledge Power? On the (Im)possibility of Learning from Strategic Interactions. NeurIPS Nivasini Ananthakrishnan, Nika Haghtalab, Chara Podimata, Kunhe Yang
2024	J	`jnl`	Leakage-Robust Bayesian Persuasion. CoRR Nika Haghtalab, Mingda Qiao, Kunhe Yang
2024	J	`jnl`	Learning With Multi-Group Guarantees For Clusterable Subpopulations. CoRR Jessica Dai, Nika Haghtalab, Eric Zhao
2024	J	`jnl`	Leveraging Reviews: Learning to Price with Buyer and Seller Uncertainty. SIGecom Exch. Wenshuo Guo, Nika Haghtalab, Kirthevasan Kandasamy, Ellen Vitercik
2024	J	`jnl`	Platforms for Efficient and Incentive-Aware Collaboration. CoRR Nika Haghtalab, Mingda Qiao, Kunhe Yang
2024	A	`conf`	Smooth Nash Equilibria: Algorithms and Complexity. ITCS Constantinos Daskalakis, Noah Golowich, Nika Haghtalab, Abhishek Shetty
2024	J	`jnl`	Smoothed Analysis with Adaptive Adversaries. J. ACM Nika Haghtalab, Tim Roughgarden, Abhishek Shetty
2024	A*	`conf`	Truthfulness of Calibration Measures. NeurIPS Nika Haghtalab, Mingda Qiao, Kunhe Yang, Eric Zhao
2024	J	`jnl`	Truthfulness of Calibration Measures. CoRR Nika Haghtalab, Mingda Qiao, Kunhe Yang, Eric Zhao
2023	A*	`conf`	A Unifying Perspective on Multi-Calibration: Game Dynamics for Multi-Objective Learning. NeurIPS Nika Haghtalab, Michael I. Jordan, Eric Zhao
2023	J	`jnl`	A Unifying Perspective on Multi-Calibration: Unleashing Game Dynamics for Multi-Objective Learning. CoRR Nika Haghtalab, Michael I. Jordan, Eric Zhao
2023	A*	`conf`	Calibrated Stackelberg Games: Learning Optimal Commitments Against Calibrated Agents. NeurIPS Nika Haghtalab, Chara Podimata, Kunhe Yang
2023	J	`jnl`	Calibrated Stackelberg Games: Learning Optimal Commitments Against Calibrated Agents. CoRR Nika Haghtalab, Chara Podimata, Kunhe Yang
2023	A*	`conf`	Competition, Alignment, and Equilibria in Digital Marketplaces. AAAI Meena Jagadeesan, Michael I. Jordan, Nika Haghtalab
2023	J	`jnl`	Delegating Data Collection in Decentralized Machine Learning. CoRR Nivasini Ananthakrishnan, Stephen Bates, Michael I. Jordan, Nika Haghtalab
2023	A*	`conf`	Improved Bayes Risk Can Yield Reduced Social Welfare Under Competition. NeurIPS Meena Jagadeesan, Michael I. Jordan, Jacob Steinhardt, Nika Haghtalab
2023	J	`jnl`	Improved Bayes Risk Can Yield Reduced Social Welfare Under Competition. CoRR Meena Jagadeesan, Michael I. Jordan, Jacob Steinhardt, Nika Haghtalab
2023	A*	`conf`	Jailbroken: How Does LLM Safety Training Fail? NeurIPS Alexander Wei, Nika Haghtalab, Jacob Steinhardt
2023	J	`jnl`	Jailbroken: How Does LLM Safety Training Fail? CoRR Alexander Wei, Nika Haghtalab, Jacob Steinhardt
2023	A*	`conf`	Leveraging Reviews: Learning to Price with Buyer and Seller Uncertainty. EC Wenshuo Guo, Nika Haghtalab, Kirthevasan Kandasamy, Ellen Vitercik
2023	J	`jnl`	Leveraging Reviews: Learning to Price with Buyer and Seller Uncertainty. CoRR Wenshuo Guo, Nika Haghtalab, Kirthevasan Kandasamy, Ellen Vitercik
2023	A*	`conf`	Open Problem: The Sample Complexity of Multi-Distribution Learning for VC Classes. COLT Pranjal Awasthi, Nika Haghtalab, Eric Zhao
2023	J	`jnl`	Smooth Nash Equilibria: Algorithms and Complexity. CoRR Constantinos Daskalakis, Noah Golowich, Nika Haghtalab, Abhishek Shetty
2023	A*	`conf`	Smoothed Analysis of Online Non-parametric Auctions. EC Naveen Durvasula, Nika Haghtalab, Manolis Zampetakis
2023	A*	`conf`	Smoothed Analysis of Sequential Probability Assignment. NeurIPS Alankrita Bhatt, Nika Haghtalab, Abhishek Shetty
2023	J	`jnl`	Smoothed Analysis of Sequential Probability Assignment. CoRR Alankrita Bhatt, Nika Haghtalab, Abhishek Shetty
2023	A*	`conf`	Stochastic Minimum Vertex Cover in General Graphs: A 3/2-Approximation. STOC Mahsa Derakhshan, Naveen Durvasula, Nika Haghtalab
2023	J	`jnl`	Stochastic Minimum Vertex Cover in General Graphs: a 3/2-Approximation. CoRR Mahsa Derakhshan, Naveen Durvasula, Nika Haghtalab
2023	J	`jnl`	The Sample Complexity of Multi-Distribution Learning for VC Classes. CoRR Pranjal Awasthi, Nika Haghtalab, Eric Zhao
2022	J	`jnl`	Communicating with Anecdotes. CoRR Nika Haghtalab, Nicole Immorlica, Brendan Lucier, Markus Mobius, Divyarthi Mohan
2022	J	`jnl`	Competition, Alignment, and Equilibria in Digital Marketplaces. CoRR Meena Jagadeesan, Michael I. Jordan, Nika Haghtalab
2022	B	`ed.`	International Conference on Algorithmic Learning Theory, 29 March - 1 April 2022, Paris, France. ALT Sanjoy Dasgupta, Nika Haghtalab
2022	A*	`conf`	Learning in Stackelberg Games with Non-myopic Agents. EC Nika Haghtalab, Thodoris Lykouris, Sloan Nietert, Alexander Wei
2022	J	`jnl`	Learning in Stackelberg Games with Non-myopic Agents. CoRR Nika Haghtalab, Thodoris Lykouris, Sloan Nietert, Alex Wei
2022	A*	`conf`	On-Demand Sampling: Learning Optimally from Multiple Distributions. NeurIPS Nika Haghtalab, Michael I. Jordan, Eric Zhao
2022	J	`jnl`	On-Demand Sampling: Learning Optimally from Multiple Distributions. CoRR Nika Haghtalab, Michael I. Jordan, Eric Zhao
2022	J	`jnl`	Oracle-Efficient Online Learning for Beyond Worst-Case Adversaries. CoRR Nika Haghtalab, Yanjun Han, Abhishek Shetty, Kunhe Yang
2022	A*	`conf`	Oracle-Efficient Online Learning for Smoothed Adversaries. NeurIPS Nika Haghtalab, Yanjun Han, Abhishek Shetty, Kunhe Yang
2021	J	`jnl`	Belief polarization in a complex world: A learning theory perspective. Proc. Natl. Acad. Sci. USA Nika Haghtalab, Matthew O. Jackson, Ariel D. Procaccia
2021	A*	`conf`	One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning. ICML Avrim Blum, Nika Haghtalab, Richard Lanas Phillips, Han Shao
2021	J	`jnl`	One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning. CoRR Avrim Blum, Nika Haghtalab, Richard Lanas Phillips, Han Shao
2021	A*	`conf`	Smoothed Analysis with Adaptive Adversaries. FOCS Nika Haghtalab, Tim Roughgarden, Abhishek Shetty
2021	J	`jnl`	Smoothed Analysis with Adaptive Adversaries. CoRR Nika Haghtalab, Tim Roughgarden, Abhishek Shetty
2021	J	`jnl`	Structured Robust Submodular Maximization: Offline and Online Algorithms. INFORMS J. Comput. Alfredo Torrico, Mohit Singh, Sebastian Pokutta, Nika Haghtalab, Joseph (Seffi) Naor, Nima Anari
2020	J	`jnl`	Ignorance Is Almost Bliss: Near-Optimal Stochastic Matching with Few Queries. Oper. Res. Avrim Blum, John P. Dickerson, Nika Haghtalab, Ariel D. Procaccia, Tuomas Sandholm, Ankit Sharma
2020	A*	`conf`	Maximizing Welfare with Incentive-Aware Evaluation Mechanisms. IJCAI Nika Haghtalab, Nicole Immorlica, Brendan Lucier, Jack Z. Wang
2020	J	`jnl`	Maximizing Welfare with Incentive-Aware Evaluation Mechanisms. CoRR Nika Haghtalab, Nicole Immorlica, Brendan Lucier, Jack Z. Wang
2020	—	`ch.`	Noise in Classification. Beyond the Worst-Case Analysis of Algorithms Maria-Florina Balcan, Nika Haghtalab
2020	J	`jnl`	Noise in Classification. CoRR Maria-Florina Balcan, Nika Haghtalab
2020	J	`jnl`	Oracle-efficient Online Learning and Auction Design. J. ACM Miroslav Dudík, Nika Haghtalab, Haipeng Luo, Robert E. Schapire, Vasilis Syrgkanis, Jennifer Wortman Vaughan
2020	A*	`conf`	Smoothed Analysis of Online and Differentially Private Learning. NeurIPS Nika Haghtalab, Tim Roughgarden, Abhishek Shetty
2020	J	`jnl`	Smoothed Analysis of Online and Differentially Private Learning. CoRR Nika Haghtalab, Tim Roughgarden, Abhishek Shetty
2020	—	`conf`	The disparate equilibria of algorithmic decision making when individuals invest rationally. FAT* Lydia T. Liu, Ashia Wilson, Nika Haghtalab, Adam Tauman Kalai, Christian Borgs, Jennifer T. Chayes
2019	C	`conf`	Algorithmic Greenlining: An Approach to Increase Diversity. AIES Christian Borgs, Jennifer T. Chayes, Nika Haghtalab, Adam Tauman Kalai, Ellen Vitercik
2019	B	`conf`	Computing Stackelberg Equilibria of Large General-Sum Games. SAGT Avrim Blum, Nika Haghtalab, MohammadTaghi Hajiaghayi, Saeed Seddighin
2019	J	`jnl`	Computing Stackelberg Equilibria of Large General-Sum Games. CoRR Avrim Blum, Nika Haghtalab, MohammadTaghi Hajiaghayi, Saeed Seddighin
2019	A	`conf`	Structured Robust Submodular Maximization: Offline and Online Algorithms. AISTATS Nima Anari, Nika Haghtalab, Seffi Naor, Sebastian Pokutta, Mohit Singh, Alfredo Torrico
2019	J	`jnl`	The Disparate Equilibria of Algorithmic Decision Making when Individuals Invest Rationally. CoRR Lydia T. Liu, Ashia Wilson, Nika Haghtalab, Adam Tauman Kalai, Christian Borgs, Jennifer T. Chayes
2019	A*	`conf`	The Provable Virtue of Laziness in Motion Planning. IJCAI Nika Haghtalab, Simon Mackenzie, Ariel D. Procaccia, Oren Salzman, Siddhartha S. Srinivasa
2019	A*	`conf`	Toward a Characterization of Loss Functions for Distribution Learning. NeurIPS Nika Haghtalab, Cameron Musco, Bo Waggoner
2019	J	`jnl`	Toward a Characterization of Loss Functions for Distribution Learning. CoRR Nika Haghtalab, Cameron Musco, Bo Waggoner
2018	A*	`conf`	Algorithms for Generalized Topic Modeling. AAAI Avrim Blum, Nika Haghtalab
2018	A*	`conf`	The Provable Virtue of Laziness in Motion Planning. ICAPS Nika Haghtalab, Simon Mackenzie, Ariel D. Procaccia, Oren Salzman, Siddhartha S. Srinivasa
2018	A*	`conf`	Weighted Voting Via No-Regret Learning. AAAI Nika Haghtalab, Ritesh Noothigattu, Ariel D. Procaccia
2017	—	`conf`	Collaborative PAC Learning. NIPS Avrim Blum, Nika Haghtalab, Ariel D. Procaccia, Mingda Qiao
2017	A*	`conf`	Efficient PAC Learning from the Crowd. COLT Pranjal Awasthi, Avrim Blum, Nika Haghtalab, Yishay Mansour
2017	J	`jnl`	Efficient PAC Learning from the Crowd. CoRR Pranjal Awasthi, Avrim Blum, Nika Haghtalab, Yishay Mansour
2017	J	`jnl`	Monitoring stealthy diffusion. Knowl. Inf. Syst. Nika Haghtalab, Aron Laszka, Ariel D. Procaccia, Yevgeniy Vorobeychik, Xenofon D. Koutsoukos
2017	—	`conf`	Online Learning with a Hint. NIPS Ofer Dekel, Arthur Flajolet, Nika Haghtalab, Patrick Jaillet
2017	A*	`conf`	Opting Into Optimal Matchings. SODA Avrim Blum, Ioannis Caragiannis, Nika Haghtalab, Ariel D. Procaccia, Eviatar B. Procaccia, Rohit Vaish
2017	A*	`conf`	Oracle-Efficient Online Learning and Auction Design. FOCS Miroslav Dudík, Nika Haghtalab, Haipeng Luo, Robert E. Schapire, Vasilis Syrgkanis, Jennifer Wortman Vaughan
2017	J	`jnl`	Robust Submodular Maximization: Offline and Online Algorithms. CoRR Nima Anari, Nika Haghtalab, Joseph Naor, Sebastian Pokutta, Mohit Singh, Alfredo Torrico
2017	J	`jnl`	The Provable Virtue of Laziness in Motion Planning. CoRR Nika Haghtalab, Simon Mackenzie, Ariel D. Procaccia, Oren Salzman, Siddhartha S. Srinivasa
2017	J	`jnl`	Weighted Voting Via No-Regret Learning. CoRR Nika Haghtalab, Ritesh Noothigattu, Ariel D. Procaccia
2016	J	`jnl`	Generalized Topic Modeling. CoRR Avrim Blum, Nika Haghtalab
2016	A*	`conf`	Learning and 1-bit Compressed Sensing under Asymmetric Noise. COLT Pranjal Awasthi, Maria-Florina Balcan, Nika Haghtalab, Hongyang Zhang
2016	J	`jnl`	Opting Into Optimal Matchings. CoRR Avrim Blum, Ioannis Caragiannis, Nika Haghtalab, Ariel D. Procaccia, Eviatar B. Procaccia, Rohit Vaish
2016	J	`jnl`	Oracle-Efficient Learning and Auction Design. CoRR Miroslav Dudík, Nika Haghtalab, Haipeng Luo, Robert E. Schapire, Vasilis Syrgkanis, Jennifer Wortman Vaughan
2016	A*	`conf`	Three Strategies to Success: Learning Adversary Models in Security Games. IJCAI Nika Haghtalab, Fei Fang, Thanh Hong Nguyen, Arunesh Sinha, Ariel D. Procaccia, Milind Tambe
2016	A*	`conf`	k-Center Clustering Under Perturbation Resilience. ICALP Maria-Florina Balcan, Nika Haghtalab, Colin White
2015	A*	`conf`	Commitment Without Regrets: Online Learning in Stackelberg Security Games. EC Maria-Florina Balcan, Avrim Blum, Nika Haghtalab, Ariel D. Procaccia
2015	A*	`conf`	Efficient Learning of Linear Separators under Bounded Noise. COLT Pranjal Awasthi, Maria-Florina Balcan, Nika Haghtalab, Ruth Urner
2015	J	`jnl`	Efficient Learning of Linear Separators under Bounded Noise. CoRR Pranjal Awasthi, Maria-Florina Balcan, Nika Haghtalab, Ruth Urner
2015	A*	`conf`	Ignorance is Almost Bliss: Near-Optimal Stochastic Matching With Few Queries. EC Avrim Blum, John P. Dickerson, Nika Haghtalab, Ariel D. Procaccia, Tuomas Sandholm, Ankit Sharma
2015	A*	`conf`	Monitoring Stealthy Diffusion. ICDM Nika Haghtalab, Aron Laszka, Ariel D. Procaccia, Yevgeniy Vorobeychik, Xenofon D. Koutsoukos
2015	J	`jnl`	Symmetric and Asymmetric $k$-center Clustering under Stability. CoRR Maria-Florina Balcan, Nika Haghtalab, Colin White
2014	A*	`conf`	Clustering in the Presence of Background Noise. ICML Shai Ben-David, Nika Haghtalab
2014	J	`jnl`	Ignorance is Almost Bliss: Near-Optimal Stochastic Matching With Few Queries. CoRR Avrim Blum, Nika Haghtalab, Ariel D. Procaccia, Ankit Sharma
2014	A*	`conf`	Lazy Defenders Are Almost Optimal against Diligent Attackers. AAAI Avrim Blum, Nika Haghtalab, Ariel D. Procaccia
2014	—	`conf`	Learning Optimal Commitment to Overcome Insecurity. NIPS Avrim Blum, Nika Haghtalab, Ariel D. Procaccia