Search Results for author: Sunil Gupta

Found 58 papers, 12 papers with code

DeepCoDA: personalized interpretability for compositional health

1 code implementation ICML 2020 Thomas Quinn, Dang Nguyen, Santu Rana, Sunil Gupta, Svetha Venkatesh

Interpretability allows the domain-expert to directly evaluate the model's relevance and reliability, a practice that offers assurance and builds trust.

Continual Learning with Dependency Preserving Hypernetworks

no code implementations16 Sep 2022 Dupati Srikar Chandra, Sakshi Varshney, P. K. Srijith, Sunil Gupta

However, the continual learning performance of existing hypernetwork based approaches are affected by the assumption of independence of the weights across the layers in order to maintain parameter efficiency.

Continual Learning Image Classification

Black-box Few-shot Knowledge Distillation

1 code implementation25 Jul 2022 Dang Nguyen, Sunil Gupta, Kien Do, Svetha Venkatesh

Traditional KD methods require lots of labeled training samples and a white-box teacher (parameters are accessible) to train a good student.

Knowledge Distillation

Defense Against Multi-target Trojan Attacks

no code implementations8 Jul 2022 Haripriya Harikumar, Santu Rana, Kien Do, Sunil Gupta, Wei Zong, Willy Susilo, Svetha Venkastesh

To defend against this attack, we first introduce a trigger reverse-engineering mechanism that uses multiple images to recover a variety of potential triggers.

Guiding Visual Question Answering with Attention Priors

no code implementations25 May 2022 Thao Minh Le, Vuong Le, Sunil Gupta, Svetha Venkatesh, Truyen Tran

This grounding guides the attention mechanism inside VQA models through a duality of mechanisms: pre-training attention weight calculation and directly guiding the weights at inference time on a case-by-case basis.

Question Answering Visual Grounding +3

Learning to Constrain Policy Optimization with Virtual Trust Region

no code implementations20 Apr 2022 Hung Le, Thommen Karimpanal George, Majid Abdolshah, Dung Nguyen, Kien Do, Sunil Gupta, Svetha Venkatesh

We introduce a constrained optimization method for policy gradient reinforcement learning, which uses a virtual trust region to regulate each policy update.

Atari Games Policy Gradient Methods

Regret Bounds for Expected Improvement Algorithms in Gaussian Process Bandit Optimization

no code implementations15 Mar 2022 Hung Tran-The, Sunil Gupta, Santu Rana, Svetha Venkatesh

In particular, whether in the noisy setting, the EI strategy with a standard incumbent converges is still an open question of the Gaussian process bandit optimization problem.

Kernel Functional Optimisation

1 code implementation NeurIPS 2021 Arun Kumar Anjanapura Venkatesh, Alistair Shilton, Santu Rana, Sunil Gupta, Svetha Venkatesh

Traditional methods for kernel selection rely on parametric kernel functions or a combination thereof and although the kernel hyperparameters are tuned, these methods often provide sub-optimal results due to the limitations induced by the parametric forms.

Bayesian Optimisation

Offline Neural Contextual Bandits: Pessimism, Optimization and Generalization

1 code implementation ICLR 2022 Thanh Nguyen-Tang, Sunil Gupta, A. Tuan Nguyen, Svetha Venkatesh

Moreover, we show that our method is more computationally efficient and has a better dependence on the effective dimension of the neural network than an online counterpart.

Multi-Armed Bandits online learning

Balanced Q-learning: Combining the Influence of Optimistic and Pessimistic Targets

no code implementations3 Nov 2021 Thommen George Karimpanal, Hung Le, Majid Abdolshah, Santu Rana, Sunil Gupta, Truyen Tran, Svetha Venkatesh

The optimistic nature of the Q-learning target leads to an overestimation bias, which is an inherent problem associated with standard $Q-$learning.

Q-Learning

Semantic Host-free Trojan Attack

no code implementations26 Oct 2021 Haripriya Harikumar, Kien Do, Santu Rana, Sunil Gupta, Svetha Venkatesh

In this paper, we propose a novel host-free Trojan attack with triggers that are fixed in the semantic space but not necessarily in the pixel space.

Expected Improvement-based Contextual Bandits

no code implementations29 Sep 2021 Hung Tran-The, Sunil Gupta, Santu Rana, Long Tran-Thanh, Svetha Venkatesh

With a linear reward function, we demonstrate that our algorithm achieves a near-optimal regret.

Multi-Armed Bandits

Neural Latent Traversal with Semantic Constraints

no code implementations29 Sep 2021 Majid Abdolshah, Hung Le, Thommen Karimpanal George, Vuong Le, Sunil Gupta, Santu Rana, Svetha Venkatesh

Whilst Generative Adversarial Networks (GANs) generate visually appealing high resolution images, the latent representations (or codes) of these models do not allow controllable changes on the semantic attributes of the generated images.

Reachability Traces for Curriculum Design in Reinforcement Learning

no code implementations29 Sep 2021 Thommen Karimpanal George, Majid Abdolshah, Hung Le, Santu Rana, Sunil Gupta, Truyen Tran, Svetha Venkatesh

The objective in goal-based reinforcement learning is to learn a policy to reach a particular goal state within the environment.

reinforcement-learning

Plug and Play, Model-Based Reinforcement Learning

no code implementations20 Aug 2021 Majid Abdolshah, Hung Le, Thommen Karimpanal George, Sunil Gupta, Santu Rana, Svetha Venkatesh

This is achieved by representing the global transition dynamics as a union of local transition functions, each with respect to one active object in the scene.

Model-based Reinforcement Learning reinforcement-learning +1

Bayesian Optimistic Optimisation with Exponentially Decaying Regret

no code implementations10 May 2021 Hung Tran-The, Sunil Gupta, Santu Rana, Svetha Venkatesh

Bayesian optimisation (BO) is a well-known efficient algorithm for finding the global optimum of expensive, black-box functions.

Bayesian Optimisation

ALT-MAS: A Data-Efficient Framework for Active Testing of Machine Learning Algorithms

no code implementations11 Apr 2021 Huong Ha, Sunil Gupta, Santu Rana, Svetha Venkatesh

Machine learning models are being used extensively in many important areas, but there is no guarantee a model will always perform well or as its developers intended.

BIG-bench Machine Learning Data Augmentation

Sample Complexity of Offline Reinforcement Learning with Deep ReLU Networks

no code implementations11 Mar 2021 Thanh Nguyen-Tang, Sunil Gupta, Hung Tran-The, Svetha Venkatesh

To the best of our knowledge, this is the first theoretical characterization of the sample complexity of offline RL with deep neural network function approximation under the general Besov regularity condition that goes beyond the traditional Reproducing Hilbert kernel spaces and Neural Tangent Kernels.

Offline RL reinforcement-learning

High Dimensional Level Set Estimation with Bayesian Neural Network

1 code implementation17 Dec 2020 Huong Ha, Sunil Gupta, Santu Rana, Svetha Venkatesh

In particular, we consider two types of LSE problems: (1) \textit{explicit} LSE problem where the threshold level is a fixed user-specified value, and, (2) \textit{implicit} LSE problem where the threshold level is defined as a percentage of the (unknown) maximum of the objective function.

Logically Consistent Loss for Visual Question Answering

no code implementations19 Nov 2020 Anh-Cat Le-Ngo, Truyen Tran, Santu Rana, Sunil Gupta, Svetha Venkatesh

We propose a new model-agnostic logic constraint to tackle this issue by formulating a logically consistent loss in the multi-task learning framework as well as a data organisation called family-batch and hybrid-batch.

Multi-Task Learning Question Answering +2

Unsupervised Anomaly Detection on Temporal Multiway Data

no code implementations20 Sep 2020 Duc Nguyen, Phuoc Nguyen, Kien Do, Santu Rana, Sunil Gupta, Truyen Tran

These include the capacity of the compact matrix LSTM to compress noisy data near perfectly, making the strategy of compressing-decompressing data ill-suited for anomaly detection under the noise.

Unsupervised Anomaly Detection

Sequential Subspace Search for Functional Bayesian Optimization Incorporating Experimenter Intuition

no code implementations8 Sep 2020 Alistair Shilton, Sunil Gupta, Santu Rana, Svetha Venkatesh

We propose an algorithm for Bayesian functional optimisation - that is, finding the function to optimise a process - guided by experimenter beliefs and intuitions regarding the expected characteristics (length-scale, smoothness, cyclicity etc.)

Bayesian Optimisation

Sub-linear Regret Bounds for Bayesian Optimisation in Unknown Search Spaces

no code implementations NeurIPS 2020 Hung Tran-The, Sunil Gupta, Santu Rana, Huong Ha, Svetha Venkatesh

To this end, we propose a novel BO algorithm which expands (and shifts) the search space over iterations based on controlling the expansion rate thought a hyperharmonic series.

Bayesian Optimisation

Distributional Reinforcement Learning via Moment Matching

1 code implementation24 Jul 2020 Thanh Tang Nguyen, Sunil Gupta, Svetha Venkatesh

We consider the problem of learning a set of probability distributions from the empirical Bellman dynamics in distributional reinforcement learning (RL), a class of state-of-the-art methods that estimate the distribution, as opposed to only the expectation, of the total return.

Atari Games Distributional Reinforcement Learning +1

Bayesian Optimization with Missing Inputs

no code implementations19 Jun 2020 Phuc Luong, Dang Nguyen, Sunil Gupta, Santu Rana, Svetha Venkatesh

In real-world applications, BO often faces a major problem of missing values in inputs.

Scalable Backdoor Detection in Neural Networks

no code implementations10 Jun 2020 Haripriya Harikumar, Vuong Le, Santu Rana, Sourangshu Bhattacharya, Sunil Gupta, Svetha Venkatesh

Recently, it has been shown that deep learning models are vulnerable to Trojan attacks, where an attacker can install a backdoor during training time to make the resultant model misidentify samples contaminated with a small trigger patch.

Randomised Gaussian Process Upper Confidence Bound for Bayesian Optimisation

1 code implementation8 Jun 2020 Julian Berk, Sunil Gupta, Santu Rana, Svetha Venkatesh

In order to improve the performance of Bayesian optimisation, we develop a modified Gaussian process upper confidence bound (GP-UCB) acquisition function.

Bayesian Optimisation

DeepCoDA: personalized interpretability for compositional health data

1 code implementation2 Jun 2020 Thomas P. Quinn, Dang Nguyen, Santu Rana, Sunil Gupta, Svetha Venkatesh

We define personalized interpretability as a measure of sample-specific feature attribution, and view it as a minimum requirement for a precision health model to justify its conclusions.

Variational Hyper-Encoding Networks

no code implementations18 May 2020 Phuoc Nguyen, Truyen Tran, Sunil Gupta, Santu Rana, Hieu-Chi Dam, Svetha Venkatesh

Given a target distribution, we predict the posterior distribution of the latent code, then use a matrix-network decoder to generate a posterior distribution q(\theta).

Density Estimation Outlier Detection +1

Incorporating Expert Prior in Bayesian Optimisation via Space Warping

no code implementations27 Mar 2020 Anil Ramachandran, Sunil Gupta, Santu Rana, Cheng Li, Svetha Venkatesh

In this paper, we represent the prior knowledge about the function optimum through a prior distribution.

Bayesian Optimisation

Incorporating Expert Prior Knowledge into Experimental Design via Posterior Sampling

no code implementations26 Feb 2020 Cheng Li, Sunil Gupta, Santu Rana, Vu Nguyen, Antonio Robles-Kelly, Svetha Venkatesh

Again, it is unknown how to incorporate the expert prior knowledge about the global optimum into Bayesian optimization process.

Experimental Design

Distributionally Robust Bayesian Quadrature Optimization

1 code implementation19 Jan 2020 Thanh Tang Nguyen, Sunil Gupta, Huong Ha, Santu Rana, Svetha Venkatesh

We adopt the distributionally robust optimization perspective to this problem by maximizing the expected objective under the most adversarial distribution.

Bayesian Optimization for Categorical and Category-Specific Continuous Inputs

1 code implementation28 Nov 2019 Dang Nguyen, Sunil Gupta, Santu Rana, Alistair Shilton, Svetha Venkatesh

To optimize such functions, we propose a new method that formulates the problem as a multi-armed bandit problem, wherein each category corresponds to an arm with its reward distribution centered around the optimum of the objective function in continuous variables.

BIG-bench Machine Learning

Trading Convergence Rate with Computational Budget in High Dimensional Bayesian Optimization

no code implementations27 Nov 2019 Hung Tran-The, Sunil Gupta, Santu Rana, Svetha Venkatesh

Optimising acquisition function in low dimensional subspaces allows our method to obtain accurate solutions within limited computational budget.

Bayesian Optimisation

Bayesian Optimization with Unknown Search Space

1 code implementation NeurIPS 2019 Huong Ha, Santu Rana, Sunil Gupta, Thanh Nguyen, Hung Tran-The, Svetha Venkatesh

Applying Bayesian optimization in problems wherein the search space is unknown is challenging.

Cost-aware Multi-objective Bayesian optimisation

no code implementations9 Sep 2019 Majid Abdolshah, Alistair Shilton, Santu Rana, Sunil Gupta, Svetha Venkatesh

We introduce a cost-aware multi-objective Bayesian optimisation with non-uniform evaluation cost over objective functions by defining cost-aware constraints over the search space.

Bayesian Optimisation

Accelerating Experimental Design by Incorporating Experimenter Hunches

no code implementations22 Jul 2019 Cheng Li, Santu Rana, Sunil Gupta, Vu Nguyen, Svetha Venkatesh, Alessandra Sutti, David Rubin, Teo Slezak, Murray Height, Mazher Mohammed, Ian Gibson

In this paper, we consider per-variable monotonic trend in the underlying property that results in a unimodal trend in those variables for a target value optimization.

Experimental Design

Sparse Spectrum Gaussian Process for Bayesian Optimization

no code implementations21 Jun 2019 Ang Yang, Cheng Li, Santu Rana, Sunil Gupta, Svetha Venkatesh

Since the balance between predictive mean and the predictive variance is the key determinant to the success of Bayesian optimization, the current sparse spectrum methods are less suitable for it.

Bayesian Optimisation

Multi-objective Bayesian optimisation with preferences over objectives

no code implementations NeurIPS 2019 Majid Abdolshah, Alistair Shilton, Santu Rana, Sunil Gupta, Svetha Venkatesh

We present a multi-objective Bayesian optimisation algorithm that allows the user to express preference-order constraints on the objectives of the type "objective A is more important than objective B".

Bayesian Optimisation

Practical Batch Bayesian Optimization for Less Expensive Functions

no code implementations5 Nov 2018 Vu Nguyen, Sunil Gupta, Santu Rana, Cheng Li, Svetha Venkatesh

Bayesian optimization (BO) and its batch extensions are successful for optimizing expensive black-box functions.

Bayesian functional optimisation with shape prior

no code implementations19 Sep 2018 Pratibha Vellanki, Santu Rana, Sunil Gupta, David Rubin de Celis Leal, Alessandra Sutti, Murray Height, Svetha Venkatesh

Real world experiments are expensive, and thus it is important to reach a target in minimum number of experiments.

Bayesian Optimisation

Accelerated Bayesian Optimization throughWeight-Prior Tuning

no code implementations21 May 2018 Alistair Shilton, Sunil Gupta, Santu Rana, Pratibha Vellanki, Laurence Park, Cheng Li, Svetha Venkatesh, Alessandra Sutti, David Rubin, Thomas Dorin, Alireza Vahid, Murray Height, Teo Slezak

In this paper we show how such auxiliary data may be used to construct a GP covariance corresponding to a more appropriate weight prior for the objective function.

Bayesian Optimisation Transfer Learning

High Dimensional Bayesian Optimization Using Dropout

no code implementations15 Feb 2018 Cheng Li, Sunil Gupta, Santu Rana, Vu Nguyen, Svetha Venkatesh, Alistair Shilton

Scaling Bayesian optimization to high dimensions is challenging task as the global optimization of high-dimensional acquisition function can be expensive and often infeasible.

Covariance Function Pre-Training with m-Kernels for Accelerated Bayesian Optimisation

no code implementations15 Feb 2018 Alistair Shilton, Sunil Gupta, Santu Rana, Pratibha Vellanki, Cheng Li, Laurence Park, Svetha Venkatesh, Alessandra Sutti, David Rubin, Thomas Dorin, Alireza Vahid, Murray Height

The paper presents a novel approach to direct covariance function learning for Bayesian optimisation, with particular emphasis on experimental design problems where an existing corpus of condensed knowledge is present.

Bayesian Optimisation Experimental Design

Process-constrained batch Bayesian optimisation

no code implementations NeurIPS 2017 Pratibha Vellanki, Santu Rana, Sunil Gupta, David Rubin, Alessandra Sutti, Thomas Dorin, Murray Height, Paul Sanders, Svetha Venkatesh

We demonstrate the performance of both pc-BO(basic) and pc-BO(nested) by optimising benchmark test functions, tuning hyper-parameters of the SVM classifier, optimising the heat-treatment process for an Al-Sc alloy to achieve target hardness, and optimising the short polymer fibre production process.

Bayesian Optimisation

High Dimensional Bayesian Optimization with Elastic Gaussian Process

no code implementations ICML 2017 Santu Rana, Cheng Li, Sunil Gupta, Vu Nguyen, Svetha Venkatesh

Bayesian optimization is an efficient way to optimize expensive black-box functions such as designing a new product with highest quality or hyperparameter tuning of a machine learning algorithm.

Budgeted Batch Bayesian Optimization With Unknown Batch Sizes

no code implementations15 Mar 2017 Vu Nguyen, Santu Rana, Sunil Gupta, Cheng Li, Svetha Venkatesh

Current batch BO approaches are restrictive in that they fix the number of evaluations per batch, and this can be wasteful when the number of specified evaluations is larger than the number of real maxima in the underlying acquisition function.

BIG-bench Machine Learning Experimental Design

Cannot find the paper you are looking for? You can Submit a new open access paper.