Zobrazeno 1 - 10
of 200
pro vyhledávání: '"Saha, Snehanshu"'
A classifier is, in its essence, a function which takes an input and returns the class of the input and implicitly assumes an underlying distribution. We argue in this article that one has to move away from this basic tenet to obtain generalisation a
Externí odkaz:
http://arxiv.org/abs/2405.11573
Detection of anomalous situations for complex mission-critical systems holds paramount importance when their service continuity needs to be ensured. A major challenge in detecting anomalies from the operational data arises due to the imbalanced class
Externí odkaz:
http://arxiv.org/abs/2402.07281
Autor:
Yedida, Rahul, Saha, Snehanshu
We propose a novel white-box approach to hyper-parameter optimization. Motivated by recent work establishing a relationship between flat minima and generalization, we first establish a relationship between the strong convexity of the loss and its fla
Externí odkaz:
http://arxiv.org/abs/2402.05025
Delivery of items from the producer to the consumer has experienced significant growth over the past decade and has been greatly fueled by the recent pandemic. Amazon Fresh, Shopify, UberEats, InstaCart, and DoorDash are rapidly growing and are shari
Externí odkaz:
http://arxiv.org/abs/2311.02017
To prune or not to prune : A chaos-causality approach to principled pruning of dense neural networks
Reducing the size of a neural network (pruning) by removing weights without impacting its performance is an important problem for resource-constrained devices. In the past, pruning was typically accomplished by ranking or penalizing weights based on
Externí odkaz:
http://arxiv.org/abs/2308.09955
The sensitivities of two periodograms are compared for weak signal planet detection in transit surveys: the widely used Box-Least Squares (BLS) algorithm following light curve detrending and the Transit Comb Filter (TCF) algorithm following autoregre
Externí odkaz:
http://arxiv.org/abs/2308.04282
Quantification of Uncertainty in predictions is a challenging problem. In the classification settings, although deep learning based models generalize well, class probabilities often lack reliability. Calibration errors are used to quantify uncertaint
Externí odkaz:
http://arxiv.org/abs/2304.12766
Autor:
Banerjee, Pronoma, Gude, Manasi V, Sampat, Rajvi J, Hedaoo, Sharvari M, Dhavala, Soma, Saha, Snehanshu
Machine learning models are often misspecified in the likelihood, which leads to a lack of robustness in the predictions. In this paper, we introduce a framework for correcting likelihood misspecifications in several paradigm agnostic noisy prior mod
Externí odkaz:
http://arxiv.org/abs/2304.03805