Publications (16)
Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
Praditha Alwis, Soumyadeep Chandra, Deepak Ravikumar +1
High-quality video datasets are foundational for training robust models in tasks like action recognition, phase detection, and event segmentation. However, many real-world video da…
Homogenizing Non-IID datasets via In-Distribution Knowledge Distillation for Decentralized Learning
Deepak Ravikumar, Gobinda Saha, Sai Aparna Aketi +1
Decentralized learning enables serverless training of deep neural networks (DNNs) in a distributed manner on multiple nodes. This allows for the use of large datasets, as well as t…
Unveiling Privacy, Memorization, and Input Curvature Links
Deepak Ravikumar, Efstathia Soufleri, Abolfazl Hashemi +1
Deep Neural Nets (DNNs) have become a pervasive tool for solving many emerging problems. However, they tend to overfit to and memorize the training set. Memorization is of keen int…
The Easy Path to Robustness: Coreset Selection using Sample Hardness
Pranav Ramesh, Arjun Roy, Deepak Ravikumar +2
Designing adversarially robust models from a data-centric perspective requires understanding which input samples are most crucial for learning resilient features. While coreset sel…
Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature
Deepak Ravikumar, Efstathia Soufleri, Kaushik Roy
In this paper, we explore the properties of loss curvature with respect to input data in deep neural networks. Curvature of loss with respect to input (termed input loss curvature)…
GradientSpace: Unsupervised Data Clustering for Improved Instruction Tuning
Shrihari Sridharan, Deepak Ravikumar, Anand Raghunathan +1
Instruction tuning is one of the key steps required for adapting large language models (LLMs) to a broad spectrum of downstream applications. However, this procedure is difficult b…
Intelligent Pooling: Proactive Resource Provisioning in Large-scale Cloud Service
Deepak Ravikumar, Alex Yeo, Yiwen Zhu +11
The proliferation of big data and analytic workloads has driven the need for cloud compute and cluster-based job processing. With Apache Spark, users can process terabytes of data…
TREND: Transferability based Robust ENsemble Design
Deepak Ravikumar, Sangamesh Kodge, Isha Garg +1
Deep Learning models hold state-of-the-art performance in many fields, but their vulnerability to adversarial examples poses threat to their ubiquitous deployment in practical sett…
Coresets from Trajectories: Selecting Data via Correlation of Loss Differences
Manish Nagaraj, Deepak Ravikumar, Kaushik Roy
Deep learning models achieve state-of-the-art performance across domains but face scalability challenges in real-time or resource-constrained scenarios. To address this, we propose…
SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise Robustness
Sangamesh Kodge, Deepak Ravikumar, Gobinda Saha +1
Label corruption, where training samples are mislabeled due to non-expert annotation or adversarial attacks, significantly degrades model performance. Acquiring large, perfectly la…
Advancing Compressed Video Action Recognition through Progressive Knowledge Distillation
Efstathia Soufleri, Deepak Ravikumar, Kaushik Roy
Compressed video action recognition classifies video samples by leveraging the different modalities in compressed videos, namely motion vectors, residuals, and intra-frames. For th…
Norm-Scaling for Out-of-Distribution Detection
Deepak Ravikumar, Kaushik Roy
Out-of-Distribution (OoD) inputs are examples that do not belong to the true underlying distribution of the dataset. Research has shown that deep neural nets make confident mispred…
Memorization Through the Lens of Curvature of Loss Function Around Samples
Isha Garg, Deepak Ravikumar, Kaushik Roy
Deep neural networks are over-parameterized and easily overfit the datasets they train on. In the extreme case, it has been shown that these networks can memorize a training set wi…
Finding the Muses: Identifying Coresets through Loss Trajectories
Manish Nagaraj, Deepak Ravikumar, Efstathia Soufleri +1
Deep learning models achieve state-of-the-art performance across domains but face scalability challenges in real-time or resource-constrained scenarios. To address this, we propose…
Exploring Vicinal Risk Minimization for Lightweight Out-of-Distribution Detection
Deepak Ravikumar, Sangamesh Kodge, Isha Garg +1
Deep neural networks have found widespread adoption in solving complex tasks ranging from image recognition to natural language processing. However, these networks make confident m…
TRIM: Token-wise Attention-Derived Saliency for Data-Efficient Instruction Tuning
Manish Nagaraj, Sakshi Choudhary, Utkarsh Saxena +2
Instruction tuning is essential for aligning large language models (LLMs) to downstream tasks and commonly relies on large, diverse corpora. However, small, high-quality subsets, k…