Related papers: KATO: Knowledge Alignment and Transfer for Transis…

Learning to optimize (L2O) is an emerging approach that leverages machine learning to develop optimization methods, aiming at reducing the laborious iterations of hand engineering. It automates the design of an optimization method based on…

Knowledge distillation transfers knowledge from a large model to a small one via task and distillation losses. In this paper, we observe a trade-off between task and distillation losses, i.e., introducing distillation loss limits the…

Analog layout synthesis faces significant challenges due to its dependence on manual processes, considerable time requirements, and performance instability. Current Bayesian Optimization (BO)-based techniques for analog layout synthesis,…

Bayesian optimization (BO) has become an effective approach for black-box function optimization problems when function evaluations are expensive and the optimum can be achieved within a relatively small number of queries. However, many…

Bayesian Optimization (BO) is an effective approach for global optimization of black-box functions when function evaluations are expensive. Most prior works use Gaussian processes to model the black-box function, however, the use of kernels…

Model-based optimization (MBO) is increasingly applied to design problems in science and engineering. A common scenario involves using a fixed training set to train models, with the goal of designing new samples that outperform those…

A transducer capable of converting quantum information stored as microwaves into telecom-wavelength signals is a critical piece of future quantum technology as it promises to enable the networking of quantum processors. Cavity…

Efficiently training control policies for robots is a major challenge that can greatly benefit from utilizing knowledge gained from training similar systems through cross-embodiment knowledge transfer. In this work, we focus on accelerating…

Bayesian optimization (BO) has for sequential optimization of expensive black-box functions demonstrated practicality and effectiveness in many real-world settings. Meta-Bayesian optimization (meta-BO) focuses on improving the sample…

Bayesian optimization (BO) struggles in high dimensions, where Gaussian-process surrogates demand heavy retraining and brittle assumptions, slowing progress on real engineering and design problems. We introduce GIT-BO, a Gradient-Informed…

Model-assisted interval designs such as the Keyboard design are transparent and easy to implement in phase I oncology trials. However, interim decisions based solely on data from the current dose may overlook informative signals from…

Conventional transfer learning leverages weights of pre-trained networks, but mandates the need for similar neural architectures. Alternatively, knowledge distillation can transfer knowledge between heterogeneous networks but often requires…

Recent work has precisely characterized the achievable trade-offs between three key information processing tasks---classical communication (generation or consumption), quantum communication (generation or consumption), and shared…

Adjustable hyperparameters of machine learning models typically impact various key trade-offs such as accuracy, fairness, robustness, or inference cost. Our goal in this paper is to find a configuration that adheres to user-specified limits…

A high fidelity fluid-structure interaction simulation may require many days to run, on hundreds of cores. This poses a serious burden, both in terms of time and economic considerations, when repetitions of such simulations may be required…

Quantization-aware training (QAT) is a leading technique for improving the accuracy of quantized neural networks. Previous work has shown that decomposing training into a full-precision (FP) phase followed by a QAT phase yields superior…

When hyperparameter optimization of a machine learning algorithm is repeated for multiple datasets it is possible to transfer knowledge to an optimization run on a new dataset. We develop a new hyperparameter-free ensemble model for…

Transfer learning has recently attracted significant research attention, as it simultaneously learns from different source domains, which have plenty of labeled data, and transfers the relevant knowledge to the target domain with limited…

Bayesian Optimization (BO) is a powerful framework for optimizing noisy, expensive-to-evaluate black-box functions. When the objective exhibits invariances under a group action, exploiting these symmetries can substantially improve BO…

Large time series models (LTMs) have emerged as powerful tools for universal forecasting, yet they often struggle with the inherent diversity and nonstationarity of real-world time series data, leading to an unsatisfactory trade-off between…