Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Pal, Ambar"'
For a hypergraph $\mathcal{H}=(X,\mathcal{E})$ a \emph{support} is a graph $G$ on $X$ such that for each $E\in\mathcal{E}$, the induced subgraph of $G$ on the elements in $E$ is connected. If $G$ is planar, we call it a planar support. A set of axis
Externí odkaz:
http://arxiv.org/abs/2410.02449
Recent work in adversarial robustness suggests that natural data distributions are localized, i.e., they place high probability in small volume regions of the input space, and that this property can be utilized for designing classifiers with improved
Externí odkaz:
http://arxiv.org/abs/2405.14176
The susceptibility of modern machine learning classifiers to adversarial examples has motivated theoretical results suggesting that these might be unavoidable. However, these results can be too general to be applicable to natural data distributions.
Externí odkaz:
http://arxiv.org/abs/2309.16096
Autor:
Pal, Ambar, Sulam, Jeremias
Randomized smoothing is a technique for providing provable robustness guarantees against adversarial attacks while making minimal assumptions about a classifier. This method relies on taking a majority vote of any base classifier over multiple noise-
Externí odkaz:
http://arxiv.org/abs/2305.04746
State-of-the-art object detectors are fast and accurate, but they require a large amount of well annotated training data to obtain good performance. However, obtaining a large amount of training annotations specific to a particular task, i.e., fine-g
Externí odkaz:
http://arxiv.org/abs/2212.00770
Autor:
Pal, Ambar, Vidal, René
Research in adversarial learning follows a cat and mouse game between attackers and defenders where attacks are proposed, they are mitigated by new defenses, and subsequently new attacks are proposed that break earlier defenses, and so on. However, i
Externí odkaz:
http://arxiv.org/abs/2009.06530
Dropout and its extensions (eg. DropBlock and DropConnect) are popular heuristics for training neural networks, which have been shown to improve generalization performance in practice. However, a theoretical understanding of their optimization and re
Externí odkaz:
http://arxiv.org/abs/1910.14186
We study the problem of answering questions about images in the harder setting, where the test questions and corresponding images contain novel objects, which were not queried about in the training data. Such setting is inevitable in real world-owing
Externí odkaz:
http://arxiv.org/abs/1704.02516
A massive current research effort focuses on combining pre-existing 'Intranets' of Things into one Internet of Things. However, this unification is not a panacea; it will expose new attack surfaces and vectors, just as it enables new applications. We
Externí odkaz:
http://arxiv.org/abs/1604.00389
A fundamental component of networking infras- tructure is the policy, used in routing tables and firewalls. Accordingly, there has been extensive study of policies. However, the theory of such policies indicates that the size of the decision tree for
Externí odkaz:
http://arxiv.org/abs/1510.07880