9 papers
A Generalisation Signal Need Not Be a Model-Selection Signal
Aditya Nagarsekar, M P Ashish Bhat, Aadi Nesarkar +5
Model selection in computational biology often relies on validation data drawn from the training regime, even when deployment lies outside it. When validation no longer preserves w…
Multi-Agent Training-free Urban Food Delivery System using Resilient UMST Network
Md Nahid Hasan, Vishwam Tiwari, Aditya Challa +2
Delivery systems have become a core part of urban life, supporting the demand for food, medicine, and other goods. Yet traditional logistics networks remain fragile, often struggli…
Matching High-Dimensional Geometric Quantiles for Test-Time Adaptation of Transformers and Convolutional Networks Alike
Sravan Danda, Aditya Challa, Shlok Mehendale +1
Test-time adaptation (TTA) refers to adapting a classifier for the test data when the probability distribution of the test data slightly differs from that of the training data of t…
Altruistic Ride Sharing: A Framework for Fair and Sustainable Urban Mobility via Peer-to-Peer Incentives
Divyanshu Singh, Ashman Mehra, Kavya Makwana +2
Urban mobility systems face persistent challenges of congestion, underutilized vehicles, and rising emissions driven by private point-to-point commuting. Although ride-sharing plat…
A Radon-Nikodým Perspective on Anomaly Detection: Theory and Implications
Shlok Mehendale, Aditya Challa, Rahul Yedida +3
Which principle underpins the design of an effective anomaly detection loss function? The answer lies in the concept of Radon-Nikodým theorem, a fundamental concept in measure theo…
A Granger-Causal Perspective on Gradient Descent with Application to Pruning
Aditya Shah, Aditya Challa, Sravan Danda +2
Stochastic Gradient Descent (SGD) is the main approach to optimizing neural networks. Several generalization properties of deep networks, such as convergence to a flatter minima, a…
Quantile Activation: Correcting a Failure Mode of ML Models
Aditya Challa, Sravan Danda, Laurent Najman +1
Standard ML models fail to infer the context distribution and suitably adapt. For instance, the learning fails when the underlying distribution is actually a mixture of distributio…
Strong convexity-guided hyper-parameter optimization for flatter losses
Rahul Yedida, Snehanshu Saha
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 establi…
Benchmarking Anomaly Detection Algorithms: Deep Learning and Beyond
Shanay Mehta, Shlok Mehendale, Nicole Fernandes +3
Detection of anomalous situations for complex mission-critical systems hold paramount importance when their service continuity needs to be ensured. A major challenge in detecting a…