no code implementations • 29 Jan 2024 • Shivanshu Shekhar, Tanishq Dubey, Koyel Mukherjee, Apoorv Saxena, Atharv Tyagi, Nishanth Kotla
In this work, we propose optimizing the usage costs of LLMs by estimating their output quality (without actually invoking the LLMs), and then solving an optimization routine for the LLM selection to either keep costs under a budget, or minimize the costs, in a quality and latency aware manner.
no code implementations • 7 Dec 2023 • Shubham Agarwal, Subrata Mitra, Sarthak Chakraborty, Srikrishna Karanam, Koyel Mukherjee, Shiv Saini
Text-to-image generation using diffusion models has seen explosive popularity owing to their ability in producing high quality images adhering to text prompts.
no code implementations • 25 Oct 2019 • Koyel Mukherjee, Alind Khare, Ashish Verma
Training neural networks on image datasets generally require extensive experimentation to find the optimal learning rate regime.
no code implementations • 24 Apr 2019 • Saurav Basu, Koyel Mukherjee, Shrihari Vasudevan
Despite the phenomenal success of deep learning in recent years, there remains a gap in understanding the fundamental mechanics of neural nets.
no code implementations • 22 Mar 2017 • Arun Rajkumar, Koyel Mukherjee, Theja Tulabandhula
For one of the four objectives, we show $NP$ hardness under the score structure and give a $\frac{1}{2}$ approximation algorithm for which no constant approximation was known thus far.