-
compressed into lightweight student models using knowledge distillation, enabling efficient real-time inference on mobile devices. The distilled models will be deployed and optimized on mobile platforms, with
-
-time, on-device applications. This project focuses on exploring model optimization strategies, including compression, quantization, and efficient architecture design, to reduce the resource footprint
-
which are friendly to privacy-enhancing techniques and on-device ML, including but not limited to model compression, quantisation, distillation, transfer learning, pruning, etc. Research Task II: Apply
-
that both parameter estimation and model selection can be interpreted as problems of data compression. The principle is simple: if we can compress data, we have learned something about its underlying