5 papers
On Optimal Steering to Achieve Exact Fairness
Mohit Sharma, Amit Jayant Deshpande, Chiranjib Bhattacharyya +1
To fix the 'bias in, bias out' problem in fair machine learning, it is important to steer feature distributions of data or internal representations of Large Language Models (LLMs)…
Cost Efficient Fairness Audit Under Partial Feedback
Nirjhar Das, Mohit Sharma, Praharsh Nanavati +2
We study the problem of auditing the fairness of a given classifier under partial feedback, where true labels are available only for positively classified individuals, (e.g., loan…
How Far Can Fairness Constraints Help Recover From Biased Data?
Mohit Sharma, Amit Deshpande
A general belief in fair classification is that fairness constraints incur a trade-off with accuracy, which biased data may worsen. Contrary to this belief, Blum & Stangl (2019) sh…
On Comparing Fair Classifiers under Data Bias
Mohit Sharma, Amit Deshpande, Rajiv Ratn Shah
In this paper, we consider a theoretical model for injecting data bias, namely, under-representation and label bias (Blum & Stangl, 2019). We empirically study the effect of varyin…
NoisyActions2M: A Multimedia Dataset for Video Understanding from Noisy Labels
Mohit Sharma, Raj Patra, Harshal Desai +3
Deep learning has shown remarkable progress in a wide range of problems. However, efficient training of such models requires large-scale datasets, and getting annotations for such…