Search Results for author:
Found 12 papers, 0 papers with code
Effective resistance in metric spaces
One attractive application of ER is to point clouds, i. e. graphs whose vertices correspond to IID samples from a distribution over a metric space.
Data-Copying in Generative Models: A Formal Framework
There has been some recent interest in detecting and addressing memorization of training data by deep neural networks.
Robust Empirical Risk Minimization with Tolerance
Developing simple, sample-efficient learning algorithms for robust classification is a pressing issue in today's tech-dominated world, and current theoretical techniques requiring exponential sample complexity and complicated improper learning rules fall far from answering the need.
Structure from Voltage
Effective resistance (ER) is an attractive way to interrogate the structure of graphs.
An Exploration of Multicalibration Uniform Convergence Bounds
Given the prevalence of ERM sample complexity bounds, our proposed framework enables machine learning practitioners to easily understand the convergence behavior of multicalibration error for a myriad of classifier architectures.
Learning what to remember
We consider a lifelong learning scenario in which a learner faces a neverending and arbitrary stream of facts and has to decide which ones to retain in its limited memory.
Online $k$-means Clustering on Arbitrary Data Streams
We propose a data parameter, $\Lambda(X)$, such that for any algorithm maintaining $O(k\text{poly}(\log n))$ centers at time $n$, there exists a data stream $X$ for which a loss of $\Omega(\Lambda(X))$ is inevitable.
Consistent Non-Parametric Methods for Maximizing Robustness
Learning classifiers that are robust to adversarial examples has received a great deal of recent attention.
No-substitution k-means Clustering with Adversarial Order
We also prove that if the data is sampled from a ``natural" distribution, such as a mixture of $k$ Gaussians, then the new complexity measure is equal to $O(k^2\log(n))$.
Sample Complexity of Adversarially Robust Linear Classification on Separated Data
This shows that for very well-separated data, convergence rates of $O(\frac{1}{n})$ are achievable, which is not the case otherwise.
When are Non-Parametric Methods Robust?
A growing body of research has shown that many classifiers are susceptible to {\em{adversarial examples}} -- small strategic modifications to test inputs that lead to misclassification.
What relations are reliably embeddable in Euclidean space?
We consider the problem of embedding a relation, represented as a directed graph, into Euclidean space.
