Search Results for author:
Found 5 papers, 0 papers with code
Towards Optimizing the Costs of LLM Usage
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.
Approximate Caching for Efficiently Serving Diffusion Models
Text-to-image generation using diffusion models has seen explosive popularity owing to their ability in producing high quality images adhering to text prompts.
A Simple Dynamic Learning Rate Tuning Algorithm For Automated Training of DNNs
Training neural networks on image datasets generally require extensive experimentation to find the optimal learning rate regime.
Layer Dynamics of Linearised Neural Nets
Despite the phenomenal success of deep learning in recent years, there remains a gap in understanding the fundamental mechanics of neural nets.
Learning to Partition using Score Based Compatibilities
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.
