16 citations · 25 across the 5 of their papers we have counts for
6 papers
LLM Compression: How Far Can We Go in Balancing Size and Performance?
Sahil Sk, Debasish Dhal, Sonal Khosla +6
Quantization is an essential and popular technique for improving the accessibility of large language models (LLMs) by reducing memory usage and computational costs while maintainin…
Challenges and Opportunities in High-dimensional Variational Inference
Akash Kumar Dhaka, Alejandro Catalina, Manushi Welandawe +3
Current black-box variational inference (BBVI) methods require the user to make numerous design choices -- such as the selection of variational objective and approximating family -…
Robust, Accurate Stochastic Optimization for Variational Inference
Akash Kumar Dhaka, Alejandro Catalina, Michael Riis Andersen +3
We consider the problem of fitting variational posterior approximations using stochastic optimization methods. The performance of these approximations depends on (1) how well the v…
Preferential Batch Bayesian Optimization
Eero Siivola, Akash Kumar Dhaka, Michael Riis Andersen +3
Most research in Bayesian optimization (BO) has focused on \emph{direct feedback} scenarios, where one has access to exact values of some expensive-to-evaluate objective. This dire…
Semi-supervised Learning with Sparse Autoencoders in Phone Classification
Akash Kumar Dhaka, Giampiero Salvi
We propose the application of a semi-supervised learning method to improve the performance of acoustic modelling for automatic speech recognition based on deep neural net- works. A…
Optimising The Input Window Alignment in CD-DNN Based Phoneme Recognition for Low Latency Processing
Akash Kumar Dhaka, Giampiero Salvi
We present a systematic analysis on the performance of a phonetic recogniser when the window of input features is not symmetric with respect to the current frame. The recogniser is…