Zobrazeno 1 - 10
of 16 240
pro vyhledávání: '"Tandon, P."'
Autor:
Zhong, Meiyu, Tandon, Ravi
Adversarial training is one of the predominant techniques for training classifiers that are robust to adversarial attacks. Recent work, however has found that adversarial training, which makes the overall classifier robust, it does not necessarily pr
Externí odkaz:
http://arxiv.org/abs/2411.14424
We propose a new approach for fine-grained uncertainty quantification (UQ) using a collision matrix. For a classification problem involving $K$ classes, the $K\times K$ collision matrix $S$ measures the inherent (aleatoric) difficulty in distinguishi
Externí odkaz:
http://arxiv.org/abs/2411.12127
The widespread adoption of language models (LMs) across multiple industries has caused huge surge in demand for GPUs. Training LMs requires tens of thousands of GPUs and housing them in the same datacenter (DCs) is becoming challenging. We focus on t
Externí odkaz:
http://arxiv.org/abs/2411.14458
Autor:
Sharma, Geetanjali, Tandon, Abhishek, Jaswal, Gaurav, Nigam, Aditya, Ramachandra, Raghavendra
Iris recognition technology plays a critical role in biometric identification systems, but their performance can be affected by variations in iris pigmentation. In this work, we investigate the impact of iris pigmentation on the efficacy of biometric
Externí odkaz:
http://arxiv.org/abs/2411.08490
In our previous works, we defined Local Information Privacy (LIP) as a context-aware privacy notion and presented the corresponding privacy-preserving mechanism. Then we claim that the mechanism satisfies epsilon-LIP for any epsilon>0 for arbitrary P
Externí odkaz:
http://arxiv.org/abs/2410.12309
Deep Neural Network (DNN) based classifiers have recently been used for the modulation classification of RF signals. These classifiers have shown impressive performance gains relative to conventional methods, however, they are vulnerable to impercept
Externí odkaz:
http://arxiv.org/abs/2410.06339
Autor:
Kashyap, Pankhi, Tandon, Pavni, Gupta, Sunny, Tiwari, Abhishek, Kulkarni, Ritwik, Jadhav, Kshitij Sharad
Long-tailed problems in healthcare emerge from data imbalance due to variability in the prevalence and representation of different medical conditions, warranting the requirement of precise and dependable classification methods. Traditional loss funct
Externí odkaz:
http://arxiv.org/abs/2410.04084
Low Rank Adaptation (LoRA) is a popular Parameter Efficient Fine Tuning (PEFT) method that effectively adapts large pre-trained models for downstream tasks. LoRA parameterizes model updates using low-rank matrices at each layer, significantly reducin
Externí odkaz:
http://arxiv.org/abs/2410.04060
Autor:
Bhattacharjee, Payel, Tandon, Ravi
Causal Graph Discovery (CGD) is the process of estimating the underlying probabilistic graphical model that represents joint distribution of features of a dataset. CGD-algorithms are broadly classified into two categories: (i) Constraint-based algori
Externí odkaz:
http://arxiv.org/abs/2409.19060
This paper considers the $\varepsilon$-differentially private (DP) release of an approximate cumulative distribution function (CDF) of the samples in a dataset. We assume that the true (approximate) CDF is obtained after lumping the data samples into
Externí odkaz:
http://arxiv.org/abs/2409.18573