10 citations · 25 across the 7 of their papers we have counts for
9 papers
Provably Learning Attention with Queries
Satwik Bhattamishra, Kulin Shah, Michael Hahn +1
We study the problem of learning Transformer-based sequence models with black-box access to their outputs. In this setting, a learner may adaptively query the oracle with any seque…
Learning Mixtures of Gaussians Using the DDPM Objective
Kulin Shah, Sitan Chen, Adam Klivans
Recent works have shown that diffusion models can learn essentially any distribution provided one can perform score estimation. Yet it remains poorly understood under what settings…
Ambient Diffusion: Learning Clean Distributions from Corrupted Data
Giannis Daras, Kulin Shah, Yuval Dagan +3
We present the first diffusion-based framework that can learn an unknown distribution using only highly-corrupted samples. This problem arises in scientific applications where acce…
RISAN: Robust Instance Specific Abstention Network
Bhavya Kalra, Kulin Shah, Naresh Manwani
In this paper, we propose deep architectures for learning instance specific abstain (reject option) binary classifiers. The proposed approach uses double sigmoid loss function as d…
Learning and Generalization in Overparameterized Normalizing Flows
Kulin Shah, Amit Deshpande, Navin Goyal
In supervised learning, it is known that overparameterized neural networks with one hidden layer provably and efficiently learn and generalize, when trained using stochastic gradie…
Rawlsian Fair Adaptation of Deep Learning Classifiers
Kulin Shah, Pooja Gupta, Amit Deshpande +1
Group-fairness in classification aims for equality of a predictive utility across different sensitive sub-populations, e.g., race or gender. Equality or near-equality constraints i…
Online Active Learning of Reject Option Classifiers
Kulin Shah, Naresh Manwani
Active learning is an important technique to reduce the number of labeled examples in supervised learning. Active learning for binary classification has been well addressed in mach…
PLUME: Polyhedral Learning Using Mixture of Experts
Kulin Shah, P. S. Sastry, Naresh Manwani
In this paper, we propose a novel mixture of expert architecture for learning polyhedral classifiers. We learn the parameters of the classifierusing an expectation maximization alg…
Sparse Reject Option Classifier Using Successive Linear Programming
Kulin Shah, Naresh Manwani
In this paper, we propose an approach for learning sparse reject option classifiers using double ramp loss . We use DC programming to find the risk minimizer. The algorithm…