25 citations · 153 across the 58 of their papers we have counts for
16 papers · 1 filter
Novel Kernel Models and Exact Representor Theory for Neural Networks Beyond the Over-Parameterized Regime
Alistair Shilton, Sunil Gupta, Santu Rana +1
This paper presents two models of neural-networks and their training applicable to neural networks of arbitrary width, depth and topology, assuming only finite-energy neural activa…
Gradient Descent in Neural Networks as Sequential Learning in RKBS
Alistair Shilton, Sunil Gupta, Santu Rana +1
The study of Neural Tangent Kernels (NTKs) has provided much needed insight into convergence and generalization properties of neural networks in the over-parametrized (wide) limit…
Combining Online Learning and Offline Learning for Contextual Bandits with Deficient Support
Hung Tran-The, Sunil Gupta, Thanh Nguyen-Tang +2
We address policy learning with logged data in contextual bandits. Current offline-policy learning algorithms are mostly based on inverse propensity score (IPS) weighting requiring…
High Dimensional Level Set Estimation with Bayesian Neural Network
Huong Ha, Sunil Gupta, Santu Rana +1
Level Set Estimation (LSE) is an important problem with applications in various fields such as material design, biotechnology, machine operational testing, etc. Existing techniques…
Sub-linear Regret Bounds for Bayesian Optimisation in Unknown Search Spaces
Hung Tran-The, Sunil Gupta, Santu Rana +2
Bayesian optimisation is a popular method for efficient optimisation of expensive black-box functions. Traditionally, BO assumes that the search space is known. However, in many pr…
Variational Hyper-Encoding Networks
Phuoc Nguyen, Truyen Tran, Sunil Gupta +3
We propose a framework called HyperVAE for encoding distributions of distributions. When a target distribution is modeled by a VAE, its neural network parameters θis drawn from a d…
Incorporating Expert Prior Knowledge into Experimental Design via Posterior Sampling
Cheng Li, Sunil Gupta, Santu Rana +3
Scientific experiments are usually expensive due to complex experimental preparation and processing. Experimental design is therefore involved with the task of finding the optimal…
Trading Convergence Rate with Computational Budget in High Dimensional Bayesian Optimization
Hung Tran-The, Sunil Gupta, Santu Rana +1
Scaling Bayesian optimisation (BO) to high-dimensional search spaces is a active and open research problems particularly when no assumptions are made on function structure. The mai…
Bayesian Optimization with Unknown Search Space
Huong Ha, Santu Rana, Sunil Gupta +3
Applying Bayesian optimization in problems wherein the search space is unknown is challenging. To address this problem, we propose a systematic volume expansion strategy for the Ba…
Accelerating Experimental Design by Incorporating Experimenter Hunches
Cheng Li, Santu Rana, Sunil Gupta +8
Experimental design is a process of obtaining a product with target property via experimentation. Bayesian optimization offers a sample-efficient tool for experimental design when…
Stable Bayesian Optimisation via Direct Stability Quantification
Alistair Shilton, Sunil Gupta, Santu Rana +3
In this paper we consider the problem of finding stable maxima of expensive (to evaluate) functions. We are motivated by the optimisation of physical and industrial processes where…
Hybrid Generative-Discriminative Models for Inverse Materials Design
Phuoc Nguyen, Truyen Tran, Sunil Gupta +2
Discovering new physical products and processes often demands enormous experimentation and expensive simulation. To design a new product with certain target characteristics, an ext…
Accelerated Bayesian Optimization throughWeight-Prior Tuning
Alistair Shilton, Sunil Gupta, Santu Rana +10
Bayesian optimization (BO) is a widely-used method for optimizing expensive (to evaluate) problems. At the core of most BO methods is the modeling of the objective function using a…
Covariance Function Pre-Training with m-Kernels for Accelerated Bayesian Optimisation
Alistair Shilton, Sunil Gupta, Santu Rana +9
The paper presents a novel approach to direct covariance function learning for Bayesian optimisation, with particular emphasis on experimental design problems where an existing cor…
Rapid Bayesian optimisation for synthesis of short polymer fiber materials
Cheng Li, David Rubin de Celis Leal, Santu Rana +6
The discovery of processes for the synthesis of new materials involves many decisions about process design, operation, and material properties. Experimentation is crucial but as co…
High Dimensional Bayesian Optimization Using Dropout
Cheng Li, Sunil Gupta, Santu Rana +3
Scaling Bayesian optimization to high dimensions is challenging task as the global optimization of high-dimensional acquisition function can be expensive and often infeasible. Exis…