11 papers
Exploring Oversmoothing with Householder Matrices
Bhaskar Karol
Deep graph neural networks(GNNs) suffer from oversmoothing- a progressive collapse of node representation towards a low information subspace as network depth increases because the…
Minibatch Selection for Language Models via Partition Matroid Constrained Gradient Matching
Prayas Agrawal, Prateek Chanda, Ishita Khatri +3
Training large language models (LLMs) on heterogeneous data requires selecting minibatches that balance convergence speed with coverage across domains. Existing methods either sele…
Online Distributional Prediction via Latent Cluster Geometry Under Drift and Corruption
Navyansh Mahla, Prateek Chanda, Ganesh Ramakrishnan
Online learning in non-stationary streams is often formulated as tracking a point estimate, but many applications require predicting the full data-generating distribution. We study…
Learning Task Mixtures from Task Affinities: A Probabilistic Graphical Model for Supervised Fine-Tuning
Prateek Chanda, Saral Sureka, Parth Pratim Chatterjee +3
Supervised fine-tuning performance for large language models depends strongly on how training budget is distributed across a heterogeneous set of tasks. In practice, mixtures are o…
UniPROT: Uniform Prototype Selection via Partial Optimal Transport with Submodular Guarantees
Prateek Chanda, Prayas Agrawal, Karthik S. Gurumoorthy +3
Selecting prototypical examples from a source distribution to represent a target data distribution is a fundamental problem in machine learning. Existing subset selection methods o…
Uncertainty-Aware Subset Selection for Robust Visual Explainability under Distribution Shifts
Madhav Gupta, Vishak Prasad C, Ganesh Ramakrishnan
Subset selection-based methods are widely used to explain deep vision models: they attribute predictions by highlighting the most influential image regions and support object-level…