Gaurush Hiranandani @gaurushh

Here to listen not to follow! Here to tell not to influence! Statistical machine learning enthusiast, machine learning for the greater-good! gaurush.com Urbana, USA Joined May 2014

Tweets

7
Followers

32
Following

53
Likes

7

Haolun Wu @Haolun_Wu0203

7 months ago

🚀 New Research Alert: Logits are All We Need to Adapt Closed Models 🔒Many commercial Large Language Models (LLMs), e.g., GPT-4, are closed-source, limiting developers to steer content generation. 🤔Can we adapt closed-source LLMs when fine-tuning or accessing their internal…

16 36 198 28K 261

Download Image

Gaurush Hiranandani @gaurushh

4 years ago

Excited to share our new work on black-box metric optimization, published at ICML'21. @sanmikoyejo Paper Link: proceedings.mlr.press/v139/hirananda… Source Code: github.com/koyejolab/fweg

0 1 1 0 1

Gaurush Hiranandani @gaurushh

5 years ago

We are excited to discuss our work at NeurIPS 2020. Read the paper for more details here arxiv.org/abs/2006.12732. We are glad to hear your comments and feedback. (n/n) #NeurIPS2020 #fairness #MachineLearning

0 0 0 0 0

Gaurush Hiranandani @gaurushh

5 years ago

Specifically, our approach elicits fair performance metrics for multiclass-multigroup classification problems, including selecting the trade-off between predictive performance and fairness violation using only a few pairwise preference comparisons. (4/n)

0 0 0 0 0

Gaurush Hiranandani @gaurushh

5 years ago

choose and customize metrics that reflect their belief of what constitutes a fair classifier. (3/n)

0 0 0 0 0

Gaurush Hiranandani @gaurushh

5 years ago

End-users often face the dilemma of identifying the best among the bouquet of metrics to measure and mitigate these biases. In our recent work with Harikrishna Narasimhan and @sanmikoyejo, we have developed a novel metric elicitation method to help end-users (2/n)

0 1 0 0 0

Gaurush Hiranandani @gaurushh

5 years ago

Over the years, algorithmic decision making has evolved to be more complex, yet existing algorithms are susceptible to biases, where decisions may be unfair to specific population subgroups. (1/n)