Bryan Kian Hsiang Low

34

Papers

3

Total Citations

Papers (34)

Incremental Quasi-Newton Methods with Faster Superlinear Convergence Rates

Towards AutoAI: Optimizing a Machine Learning System with Black-box and Differentiable Components

Zeroth-Order Methods for Constrained Nonconvex Nonsmooth Stochastic Optimization

Deletion-Anticipative Data Selection with a Limited Budget

Distributionally Robust Data Valuation

Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers

Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions

Inverse Reinforcement Learning with Locally Consistent Reward Functions

Decentralized Sum-of-Nonconvex Optimization

DeRDaVa: Deletion-Robust Data Valuation for Machine Learning

Paid with Models: Optimal Contract Design for Collaborative Machine Learning

Trade-off between Payoff and Model Rewards in Shapley-Fair Collaborative Machine Learning

Unifying and Boosting Gradient-Based Training-Free Neural Architecture Search

Bayesian Optimization with Cost-varying Variable Subsets

Exploiting Correlated Auxiliary Feedback in Parameterized Bandits

Incentives in Private Collaborative Machine Learning

Quantum Bayesian Optimization

Batch Bayesian Optimization For Replicable Experimental Design

Model Shapley: Equitable Model Valuation with Black-box Access

A Unifying Framework of Anytime Sparse Gaussian Process Regression Models with Stochastic Variational Inference for Big Data

A Distributed Variational Inference Framework for Unifying Parallel Sparse Gaussian Process Regression Models

Distributed Batch Gaussian Process Optimization

Bayesian Optimization Meets Bayesian Optimal Stopping

Collective Model Fusion for Multiple Black-Box Experts

Implicit Posterior Variational Inference for Deep Gaussian Processes

Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimization

Federated Bayesian Optimization via Thompson Sampling

Variational Bayesian Unlearning

Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee

Optimizing Conditional Value-At-Risk of Black-Box Functions

Differentially Private Federated Bayesian Optimization with Distributed Exploration

Validation Free and Replication Robust Volume-based Data Valuation

Gradient Driven Rewards to Guarantee Fairness in Collaborative Machine Learning

Sample-Then-Optimize Batch Neural Thompson Sampling