16 citations · 27 across the 11 of their papers we have counts for
12 papers
Pluralistic Leaderboards
Nika Haghtalab, Ariel D. Procaccia, Han Shao +2
Recent leaderboard-based evaluations of large language models aggregate user feedback by fitting a Bradley--Terry model to pairwise comparisons, producing a single global ranking b…
Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?
Paul Gölz, Nika Haghtalab, Kunhe Yang
After pre-training, large language models are aligned with human preferences based on pairwise comparisons. State-of-the-art alignment methods (such as PPO-based RLHF and DPO) are…
Leakage-Robust Bayesian Persuasion
Nika Haghtalab, Mingda Qiao, Kunhe Yang
This paper introduces leakage-robust Bayesian persuasion. Situated between public Bayesian persuasion [KG11] (and its multi-receiver variants [CCG23, Xu20]) and private Bayesian pe…
Is Knowledge Power? On the (Im)possibility of Learning from Strategic Interactions
Nivasini Ananthakrishnan, Nika Haghtalab, Chara Podimata +1
When learning in strategic environments, a key question is whether agents can overcome uncertainty about their preferences to achieve outcomes they could have achieved absent any u…
Truthfulness of Calibration Measures
Nika Haghtalab, Mingda Qiao, Kunhe Yang +1
We initiate the study of the truthfulness of calibration measures in sequential prediction. A calibration measure is said to be truthful if the forecaster (approximately) minimizes…
Platforms for Efficient and Incentive-Aware Collaboration
Nika Haghtalab, Mingda Qiao, Kunhe Yang
Collaboration is crucial for reaching collective goals. However, its effectiveness is often undermined by the strategic behavior of individual agents -- a fact that is captured by…
Calibrated Stackelberg Games: Learning Optimal Commitments Against Calibrated Agents
Nika Haghtalab, Chara Podimata, Kunhe Yang
We introduce \emph{Calibrated Stackelberg Games (CSGs)}, a generalization of the standard Stackelberg Games (SGs) framework. In CSGs, a principal repeatedly interacts with an agent…
Fundamental Bounds on Online Strategic Classification
Saba Ahmadi, Avrim Blum, Kunhe Yang
We study the problem of online binary classification where strategic agents can manipulate their observable features in predefined ways, modeled by a manipulation graph, in order t…
Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian
Paria Rashidinejad, Hanlin Zhu, Kunhe Yang +2
Offline reinforcement learning (RL), which refers to decision-making from a previously-collected dataset of interactions, has received significant attention over the past years. Mu…
Oracle-Efficient Online Learning for Beyond Worst-Case Adversaries
Nika Haghtalab, Yanjun Han, Abhishek Shetty +1
In this paper, we study oracle-efficient algorithms for beyond worst-case analysis of online learning. We focus on two settings. First, the smoothed analysis setting of [RST11,HRS2…
Nudge: Stochastically Improving upon FCFS
Isaac Grosof, Kunhe Yang, Ziv Scully +1
The First-Come First-Served (FCFS) scheduling policy is the most popular scheduling algorithm used in practice. Furthermore, its usage is theoretically validated: for light-tailed…
-learning with Logarithmic Regret
Kunhe Yang, Lin F. Yang, Simon S. Du
This paper presents the first non-asymptotic result showing that a model-free algorithm can achieve a logarithmic cumulative regret for episodic tabular reinforcement learning if t…