Search Results for author:
Found 15 papers, 0 papers with code
Simplifying Adversarially Robust PAC Learning with Tolerance
Adversarially robust PAC learning has proved to be challenging, with the currently best known learners [Montasser et al., 2021a] relying on improper methods based on intricate compression schemes, resulting in sample complexity exponential in the VC-dimension.
On the Computability of Multiclass PAC Learning
We focus on the case of finite label space and start by proposing a computable version of the Natarajan dimension and showing that it characterizes CPAC learnability in this setting.
Calibration through the Lens of Interpretability
Calibration is a frequently invoked concept when useful label probability estimates are required on top of classification accuracy.
On the Computability of Robust PAC Learning
We initiate the study of computability requirements for adversarially robust learning.
Learning Losses for Strategic Classification
We analyse the sample complexity for a known graph of possible manipulations in terms of the complexity of the function class and the manipulation graph.
Adversarially Robust Learning with Tolerance
In the tolerant version, the error of the learner is compared with the best achievable error with respect to a slightly larger perturbation radius $(1+\gamma)r$.
On the (Un-)Avoidability of Adversarial Examples
The phenomenon of adversarial examples in deep learning models has caused substantial concern over their reliability.
Black-box Certification and Learning under Adversarial Perturbations
We formally study the problem of classification under adversarial perturbations from a learner's perspective as well as a third-party who aims at certifying the robustness of a given black-box classifier.
On Learnability with Computable Learners
We initiate a study of learning with computable learners and computable output predictors.
When can unlabeled data improve the learning rate?
In semi-supervised classification, one is given access both to labeled and unlabeled data.
Lifelong Learning with Weighted Majority Votes
Better understanding of the potential benefits of information transfer and representation learning is an important step towards the goal of building intelligent systems that are able to persist in the world and learn over time.
Active Nearest-Neighbor Learning in Metric Spaces
We propose a pool-based non-parametric active learning algorithm for general metric spaces, called MArgin Regularized Metric Active Nearest Neighbor (MARMANN), which outputs a nearest-neighbor classifier.
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 Economic Parameters from Revealed Preferences
In this work we advance this line of work by providing sample complexity guarantees and efficient algorithms for a number of important classes.
Generative Multiple-Instance Learning Models For Quantitative Electromyography
We present a comprehensive study of the use of generative modeling approaches for Multiple-Instance Learning (MIL) problems.
