Showing stat.MLShow all
2 papers · 1 filter
stat.ML2026
From Collapse to Improvement: Statistical Perspectives on the Evolutionary Dynamics of Iterative Training on Contaminated Sources
Soham Bakshi, Sunrit Chakraborty
The problem of model collapse has presented new challenges in iterative training of generative models, where such training with synthetic data leads to an overall degradation of pe…
stat.ML2023
Bayes classifier cannot be learned from noisy responses with unknown noise rates
Soham Bakshi, Subha Maity
Training a classifier with noisy labels typically requires the learner to specify the distribution of label noise, which is often unknown in practice. Although there have been some…