Search Results for author:
Found 32 papers, 4 papers with code
Learning With Multi-Group Guarantees For Clusterable Subpopulations
A canonical desideratum for prediction problems is that performance guarantees should hold not just on average over the population, but also for meaningful subpopulations within the overall population.
Algorithmic Content Selection and the Impact of User Disengagement
The content selection problem of digital services is often modeled as a decision-process where a service chooses, over multiple rounds, an arm to pull from a set of arms that each return a certain reward.
Is Knowledge Power? On the (Im)possibility of Learning from Strategic Interactions
On the other hand, if both players start with some uncertainty about the game, the quality of information alone does not determine which agent can achieve her Stackelberg value.
Truthfulness of Calibration Measures
A calibration measure is said to be truthful if the forecaster (approximately) minimizes the expected penalty by predicting the conditional expectation of the next outcome, given the prior distribution of outcomes.
Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation
Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs.
Can Probabilistic Feedback Drive User Impacts in Online Platforms?
A common explanation for negative user impacts of content recommender systems is misalignment between the platform's objective and user welfare.
Smooth Nash Equilibria: Algorithms and Complexity
We show that both weak and strong $\sigma$-smooth Nash equilibria have superior computational properties to Nash equilibria: when $\sigma$ as well as an approximation parameter $\epsilon$ and the number of players are all constants, there is a constant-time randomized algorithm to find a weak $\epsilon$-approximate $\sigma$-smooth Nash equilibrium in normal-form games.
Delegating Data Collection in Decentralized Machine Learning
Motivated by the emergence of decentralized machine learning (ML) ecosystems, we study the delegation of data collection.
The Sample Complexity of Multi-Distribution Learning for VC Classes
Multi-distribution learning is a natural generalization of PAC learning to settings with multiple data distributions.
Improved Bayes Risk Can Yield Reduced Social Welfare Under Competition
As the scale of machine learning models increases, trends such as scaling laws anticipate consistent downstream improvements in predictive accuracy.
Leveraging Reviews: Learning to Price with Buyer and Seller Uncertainty
Customers with few relevant reviews may hesitate to make a purchase except at a low price, so for the seller, there is a tension between setting high prices and ensuring that there are enough reviews so that buyers can confidently estimate their values.
On-Demand Sampling: Learning Optimally from Multiple Distributions
This improves upon the best known sample complexity bounds for fair federated learning by Mohri et al. and collaborative learning by Nguyen and Zakynthinou by multiplicative factors of $n$ and $\log(n)/\epsilon^3$, respectively.
Competition, Alignment, and Equilibria in Digital Marketplaces
Nonetheless, the data sharing assumptions impact what mechanism drives misalignment and also affect the specific form of misalignment (e. g. the quality of the best-case and worst-case market outcomes).
Learning in Stackelberg Games with Non-myopic Agents
Although learning in Stackelberg games is well-understood when the agent is myopic, dealing with non-myopic agents poses additional complications.
Oracle-Efficient Online Learning for Beyond Worst-Case Adversaries
For the smoothed analysis setting, our results give the first oracle-efficient algorithm for online learning with smoothed adversaries [HRS22].
One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning
In recent years, federated learning has been embraced as an approach for bringing about collaboration across large populations of learning agents.
Smoothed Analysis with Adaptive Adversaries
-Online discrepancy minimization: We consider the online Koml\'os problem, where the input is generated from an adaptive sequence of $\sigma$-smooth and isotropic distributions on the $\ell_2$ unit ball.
Maximizing Welfare with Incentive-Aware Evaluation Mechanisms
The goal is to design an evaluation mechanism that maximizes the overall quality score, i. e., welfare, in the population, taking any strategic updating into account.
Noise in Classification
This chapter considers the computational and statistical aspects of learning linear thresholds in presence of noise.
Smoothed Analysis of Online and Differentially Private Learning
Practical and pervasive needs for robustness and privacy in algorithms have inspired the design of online adversarial and differentially private learning algorithms.
Toward a Characterization of Loss Functions for Distribution Learning
We aim to understand this fact, taking an axiomatic approach to the design of loss functions for learning distributions.
Collaborative PAC Learning
We introduce a collaborative PAC learning model, in which k players attempt to learn the same underlying concept.
Online Learning with a Hint
We show that the player can benefit from such a hint if the set of feasible actions is sufficiently round.
The Provable Virtue of Laziness in Motion Planning
The Lazy Shortest Path (LazySP) class consists of motion-planning algorithms that only evaluate edges along shortest paths between the source and target.
Robotics Data Structures and Algorithms
Efficient PAC Learning from the Crowd
When a noticeable fraction of the labelers are perfect, and the rest behave arbitrarily, we show that any $\mathcal{F}$ that can be efficiently learned in the traditional realizable PAC model can be learned in a computationally efficient manner by querying the crowd, despite high amounts of noise in the responses.
Oracle-Efficient Online Learning and Auction Design
We consider the design of computationally efficient online learning algorithms in an adversarial setting in which the learner has access to an offline optimization oracle.
Generalized Topic Modeling
In standard topic models, a topic (such as sports, business, or politics) is viewed as a probability distribution $\vec a_i$ over words, and a document is generated by first selecting a mixture $\vec w$ over topics, and then generating words i. i. d.
$k$-center Clustering under Perturbation Resilience
In this work, we take this approach and provide strong positive results both for the asymmetric and symmetric $k$-center problems under a natural input stability (promise) condition called $\alpha$-perturbation resilience [Bilu and Linia 2012], which states that the optimal solution does not change under any alpha-factor perturbation to the input distances.
Efficient Learning of Linear Separators under Bounded Noise
We provide the first polynomial time algorithm that can learn linear separators to arbitrarily small excess error in this noise model under the uniform distribution over the unit ball in $\Re^d$, for some constant value of $\eta$.
Learning Optimal Commitment to Overcome Insecurity
Game-theoretic algorithms for physical security have made an impressive real-world impact.
