Search Results for author:
Found 40 papers, 5 papers with code
Nearly-tight Approximation Guarantees for the Improving Multi-Armed Bandits Problem
We give nearly-tight upper and lower bounds for the improving multi-armed bandits problem.
Dueling Optimization with a Monotone Adversary
We introduce and study the problem of dueling optimization with a monotone adversary, which is a generalization of (noiseless) dueling convex optimization.
On the Vulnerability of Fairness Constrained Learning to Malicious Noise
For example, for Demographic Parity we show we can incur only a $\Theta(\alpha)$ loss in accuracy, where $\alpha$ is the malicious noise rate, matching the best possible even without fairness constraints.
Strategic Classification under Unknown Personalized Manipulation
Ball manipulations are a widely studied class of manipulations in the literature, where agents can modify their feature vector within a bounded radius ball.
Agnostic Multi-Robust Learning Using ERM
A fundamental problem in robust learning is asymmetry: a learner needs to correctly classify every one of exponentially-many perturbations that an adversary might make to a test-time natural example.
Fundamental Bounds on Online Strategic Classification
For instance, whereas in the non-strategic case, a mistake bound of $\ln|H|$ is achievable via the halving algorithm when the target function belongs to a known class $H$, we show that no deterministic algorithm can achieve a mistake bound $o(\Delta)$ in the strategic setting, where $\Delta$ is the maximum degree of the manipulation graph (even when $|H|=O(\Delta)$).
Multi Stage Screening: Enforcing Fairness and Maximizing Efficiency in a Pre-Existing Pipeline
Even if the firm is required to interview all of those who pass the final round, the tests themselves could have the property that qualified individuals from some groups pass more easily than qualified individuals from others.
Robustly-reliable learners under poisoning attacks
Remarkably, we provide a complete characterization of learnability in this setting, in particular, nearly-tight matching upper and lower bounds on the region that can be certified, as well as efficient algorithms for computing this region given an ERM oracle.
On classification of strategic agents who can both game and improve
For the general discrete model, we give an efficient algorithm for the problem of maximizing the number of true positives subject to no false positives, and show how to extend this to a partial-information learning setting.
Setting Fair Incentives to Maximize Improvement
A key technical challenge of this problem is the non-monotonicity of social welfare in the set of target levels, i. e., adding a new target level may decrease the total amount of improvement as it may get easier for some agents to improve.
A Theory of PAC Learnability under Transformation Invariances
One interesting observation is that distinguishing between the original data and the transformed data is necessary to achieve optimal accuracy in setting (ii) and (iii), which implies that any algorithm not differentiating between the original and transformed data (including data augmentation) is not optimal.
Boosting Barely Robust Learners: A New Perspective on Adversarial Robustness
We present an oracle-efficient algorithm for boosting the adversarial robustness of barely robust learners.
Excess Capacity and Backdoor Poisoning
A backdoor data poisoning attack is an adversarial attack wherein the attacker injects several watermarked, mislabeled training examples into a training set.
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.
Robust learning under clean-label attack
We study the problem of robust learning under clean-label data-poisoning attacks, where the attacker injects (an arbitrary set of) correctly-labeled examples to the training set to fool the algorithm into making mistakes on specific test instances at test time.
Communication-Aware Collaborative Learning
In this paper, we study collaborative PAC learning with the goal of reducing communication cost at essentially no penalty to the sample complexity.
Online Learning with Primary and Secondary Losses
On the positive side, we show that running any switching-limited algorithm can achieve this goal if all experts satisfy the assumption that the secondary loss does not exceed the linear threshold by $o(T)$ for any time interval.
An Analysis of Robustness of Non-Lipschitz Networks
Despite significant advances, deep networks remain highly susceptible to adversarial attack.
Active Local Learning
In particular, the number of label queries should be independent of the complexity of $H$, and the function $h$ should be well-defined, independent of $x$.
The Strategic Perceptron
The classical Perceptron algorithm provides a simple and elegant procedure for learning a linear classifier.
Learning Complexity of Simulated Annealing
A key component that plays a crucial role in the performance of simulated annealing is the criteria under which the temperature changes namely, the cooling schedule.
Random Smoothing Might be Unable to Certify $\ell_\infty$ Robustness for High-Dimensional Images
We show a hardness result for random smoothing to achieve certified adversarial robustness against attacks in the $\ell_p$ ball of radius $\epsilon$ when $p>2$.
Recovering from Biased Data: Can Fairness Constraints Improve Accuracy?
Multiple fairness constraints have been proposed in the literature, motivated by a range of concerns about how demographic groups might be treated unfairly by machine learning classifiers.
Advancing subgroup fairness via sleeping experts
We demonstrate that the task of satisfying this guarantee for multiple overlapping groups is not straightforward and show that for the simple objective of unweighted average of false negative and false positive rate, satisfying this for overlapping populations can be statistically impossible even when we are provided predictors that perform well separately on each subgroup.
On preserving non-discrimination when combining expert advice
We study the interplay between sequential decision making and avoiding discrimination against protected groups, when examples arrive online and do not follow distributional assumptions.
Collaborative PAC Learning
We introduce a collaborative PAC learning model, in which k players attempt to learn the same underlying concept.
Active Tolerant Testing
In this work, we give the first algorithms for tolerant testing of nontrivial classes in the active model: estimating the distance of a target function to a hypothesis class C with respect to some arbitrary distribution D, using only a small number of label queries to a polynomial-sized pool of unlabeled examples drawn from D. Specifically, we show that for the class D of unions of d intervals on the line, we can estimate the error rate of the best hypothesis in the class to an additive error epsilon from only $O(\frac{1}{\epsilon^6}\log \frac{1}{\epsilon})$ label queries to an unlabeled pool of size $O(\frac{d}{\epsilon^2}\log \frac{1}{\epsilon})$.
Lifelong Learning in Costly Feature Spaces
An important long-term goal in machine learning systems is to build learning agents that, like humans, can learn many tasks over their lifetime, and moreover use information from these tasks to improve their ability to do so efficiently.
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.
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.
Sparse Approximation via Generating Point Sets
]{#1\left({#2}\right)} \newcommand{\npoints}{n} \newcommand{\ballD}{\mathsf{b}} \newcommand{\dataset}{{P}} $ For a set $\dataset$ of $\npoints$ points in the unit ball $\ballD \subseteq \Re^d$, consider the problem of finding a small subset $\algset \subseteq \dataset$ such that its convex-hull $\eps$-approximates the convex-hull of the original set.
The Ladder: A Reliable Leaderboard for Machine Learning Competitions
In this work, we introduce a notion of "leaderboard accuracy" tailored to the format of a competition.
Learning Optimal Commitment to Overcome Insecurity
Game-theoretic algorithms for physical security have made an impressive real-world impact.
Efficient Representations for Life-Long Learning and Autoencoding
Specifically, we consider the problem of learning many different target functions over time, that share certain commonalities that are initially unknown to the learning algorithm.
Learning Mixtures of Ranking Models
We present the first polynomial time algorithm which provably learns the parameters of a mixture of two Mallows models.
Active Learning and Best-Response Dynamics
We examine an important setting for engineered systems in which low-power distributed sensors are each making highly noisy measurements of some unknown target function.
Differentially Private Data Analysis of Social Networks via Restricted Sensitivity
Specifically, given a query f and a hypothesis H about the structure of a dataset D, we show generically how to transform f into a new query f_H whose global sensitivity (over all datasets including those that do not satisfy H) matches the restricted sensitivity of the query f. Moreover, if the belief of the querier is correct (i. e., D is in H) then f_H(D) = f(D).
Cryptography and Security Social and Information Networks Physics and Society
Trading off Mistakes and Don't-Know Predictions
If the number of don't know predictions is forced to be zero, the model reduces to the well-known mistake-bound model introduced by Littlestone [Lit88].
Tracking Dynamic Sources of Malicious Activity at Internet Scale
We formulate and address the problem of discovering dynamic malicious regions on the Internet.
Noise-Tolerant Learning, the Parity Problem, and the Statistical Query Model
Hence this natural extension to the statistical query model does not increase the set of weakly learnable functions.
