Search Results for author:
Found 50 papers, 21 papers with code
Outsourced Bayesian Optimization
This paper presents the outsourced-Gaussian process-upper confidence bound (O-GP-UCB) algorithm, which is the first algorithm for privacy-preserving Bayesian optimization (BO) in the outsourced setting with a provable performance guarantee.
Learning Task-Agnostic Embedding of Multiple Black-Box Experts for Multi-Task Model Fusion
The task-agnostic prototypes can then be reintegrated to generate a new model that solves a new task encoded with a different prototype distribution.
PINNACLE: PINN Adaptive ColLocation and Experimental points selection
Physics-Informed Neural Networks (PINNs), which incorporate PDEs as soft constraints, train with a composite loss function that contains multiple training point types: different types of collocation points chosen during training to enforce each PDE and initial/boundary conditions, and experimental points which are usually costly to obtain via experiments or simulations.
Incentives in Private Collaborative Machine Learning
Finally, the mediator rewards each party with different posterior samples of the model parameters.
Robustifying and Boosting Training-Free Neural Architecture Search
Nevertheless, the estimation ability of these metrics typically varies across different tasks, making it challenging to achieve robust and consistently good search performance on diverse tasks with only a single training-free metric.
Localized Zeroth-Order Prompt Optimization
Existing methodologies usually prioritize a global optimization for finding the global optimum, which however will perform poorly in certain tasks.
Decentralized Sum-of-Nonconvex Optimization
However, the convergence rate of the PMGT-SVRG algorithm has a linear dependency on the condition number, which is undesirable for the ill-conditioned problem.
Incremental Quasi-Newton Methods with Faster Superlinear Convergence Rates
The recently proposed incremental quasi-Newton method is based on BFGS update and achieves a local superlinear convergence rate that is dependent on the condition number of the problem.
Understanding Domain Generalization: A Noise Robustness Perspective
Despite the rapid development of machine learning algorithms for domain generalization (DG), there is no clear empirical evidence that the existing DG algorithms outperform the classic empirical risk minimization (ERM) across standard benchmarks.
DeRDaVa: Deletion-Robust Data Valuation for Machine Learning
Data valuation is concerned with determining a fair valuation of data from data sources to compensate them or to identify training examples that are the most or least useful for predictions.
Use Your INSTINCT: INSTruction optimization usIng Neural bandits Coupled with Transformers
We perform instruction optimization for ChatGPT and use extensive experiments to show that our INSTINCT consistently outperforms the existing methods in different tasks, such as in various instruction induction tasks and the task of improving the zero-shot chain-of-thought instruction.
WASA: WAtermark-based Source Attribution for Large Language Model-Generated Data
The impressive performances of large language models (LLMs) and their immense potential for commercialization have given rise to serious concerns over the intellectual property (IP) of their training data.
Federated Zeroth-Order Optimization using Trajectory-Informed Surrogate Gradients
To this end, we (a) introduce trajectory-informed gradient surrogates which is able to use the history of function queries during optimization for accurate and query-efficient gradient estimation, and (b) develop the technique of adaptive gradient correction using these gradient surrogates to mitigate the aforementioned disparity.
Hessian-Aware Bayesian Optimization for Decision Making Systems
Derivative-free approaches such as Bayesian Optimization mitigate the dependency on the quality of gradient feedback, but are known to scale poorly in the high-dimension setting of complex decision making systems.
Fair yet Asymptotically Equal Collaborative Learning
In collaborative learning with streaming data, nodes (e. g., organizations) jointly and continuously learn a machine learning (ML) model by sharing the latest model updates computed from their latest streaming data.
Training-Free Neural Active Learning with Initialization-Robustness Guarantees
To this end, we introduce our expected variance with Gaussian processes (EV-GP) criterion for neural active learning, which is theoretically guaranteed to select data points which lead to trained NNs with both (a) good predictive performances and (b) initialization robustness.
Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks
We introduce Goat, a fine-tuned LLaMA model that significantly outperforms GPT-4 on a range of arithmetic tasks.
Fine-tuning Language Models with Generative Adversarial Reward Modelling
Reinforcement Learning with Human Feedback (RLHF) has been demonstrated to significantly enhance the performance of large language models (LLMs) by aligning their outputs with desired human values through instruction tuning.
FedHQL: Federated Heterogeneous Q-Learning
Federated Reinforcement Learning (FedRL) encourages distributed agents to learn collectively from each other's experience to improve their performance without exchanging their raw trajectories.
Sample-Then-Optimize Batch Neural Thompson Sampling
linear model), which is equivalently sampled from the GP posterior with the NTK as the kernel function.
Bayesian Optimization under Stochastic Delayed Feedback
The existing BO methods assume that the function evaluation (feedback) is available to the learner immediately or after a fixed delay.
On Provably Robust Meta-Bayesian Optimization
We prove that both algorithms are asymptotically no-regret even when some or all previous tasks are dissimilar to the current task, and show that RM-GP-UCB enjoys a better theoretical robustness than RM-GP-TS.
Federated Neural Bandits
To better exploit the federated setting, FN-UCB adopts a weighted combination of two UCBs: $\text{UCB}^{a}$ allows every agent to additionally use the observations from the other agents to accelerate exploration (without sharing raw observations), while $\text{UCB}^{b}$ uses an NN with aggregated parameters for reward prediction in a similar way to federated averaging for supervised learning.
On the Convergence of the Shapley Value in Parametric Bayesian Learning Games
We show that for any two players, under some regularity conditions, their difference in Shapley value converges in probability to the difference in Shapley value of a limiting game whose characteristic function is proportional to the log-determinant of the joint Fisher information.
Adjusted Expected Improvement for Cumulative Regret Minimization in Noisy Bayesian Optimization
To adapt the EI for better performance under cumulative regret, we introduce a novel quantity called the evaluation cost which is compared against the acquisition function, and with this, develop the expected improvement-cost (EIC) algorithm.
Markov Chain Monte Carlo-Based Machine Unlearning: Unlearning What Needs to be Forgotten
Similarly, MCU can be used to erase the lineage of a user's personal data from trained ML models, thus upholding a user's "right to be forgotten".
Rectified Max-Value Entropy Search for Bayesian Optimization
Although the existing max-value entropy search (MES) is based on the widely celebrated notion of mutual information, its empirical performance can suffer due to two misconceptions whose implications on the exploration-exploitation trade-off are investigated in this paper.
Unifying and Boosting Gradient-Based Training-Free Neural Architecture Search
As a consequence, (a) the relationships among these metrics are unclear, (b) there is no theoretical interpretation for their empirical performances, and (c) there may exist untapped potential in existing training-free NAS, which probably can be unveiled through a unified theoretical understanding.
Incentivizing Collaboration in Machine Learning via Synthetic Data Rewards
This paper presents a novel collaborative generative modeling (CGM) framework that incentivizes collaboration among self-interested parties to contribute data to a pool for training a generative model (e. g., GAN), from which synthetic data are drawn and distributed to the parties as rewards commensurate to their contributions.
Optimizing Conditional Value-At-Risk of Black-Box Functions
This paper presents two Bayesian optimization (BO) algorithms with theoretical performance guarantee to maximize the conditional value-at-risk (CVaR) of a black-box function: CV-UCB and CV-TS which are based on the well-established principle of optimism in the face of uncertainty and Thompson sampling, respectively.
Gradient Driven Rewards to Guarantee Fairness in Collaborative Machine Learning
In this paper, we adopt federated learning as a gradient-based formalization of collaborative machine learning, propose a novel cosine gradient Shapley value to evaluate the agents’ uploaded model parameter updates/gradients, and design theoretically guaranteed fair rewards in the form of better model performance.
Validation Free and Replication Robust Volume-based Data Valuation
We observe that the diversity of the data points is an inherent property of the dataset that is independent of validation.
Differentially Private Federated Bayesian Optimization with Distributed Exploration
The resulting differentially private FTS with DE (DP-FTS-DE) algorithm is endowed with theoretical guarantees for both the privacy and utility and is amenable to interesting theoretical insights about the privacy-utility trade-off.
Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee
The growing literature of Federated Learning (FL) has recently inspired Federated Reinforcement Learning (FRL) to encourage multiple agents to federatively build a better decision-making policy without sharing raw trajectories.
Neural Ensemble Search via Bayesian Sampling
Unfortunately, these NAS algorithms aim to select only one single well-performing architecture from their search spaces and thus have overlooked the capability of neural network ensemble (i. e., an ensemble of neural networks with diverse architectures) in achieving improved performance over a single final selected architecture.
NASI: Label- and Data-agnostic Neural Architecture Search at Initialization
Recent years have witnessed a surging interest in Neural Architecture Search (NAS).
Trusted-Maximizers Entropy Search for Efficient Bayesian Optimization
Information-based Bayesian optimization (BO) algorithms have achieved state-of-the-art performance in optimizing a black-box objective function.
Value-at-Risk Optimization with Gaussian Processes
Value-at-risk (VaR) is an established measure to assess risks in critical real-world applications with random environmental factors.
Convolutional Normalizing Flows for Deep Gaussian Processes
Deep Gaussian processes (DGPs), a hierarchical composition of GP models, have successfully boosted the expressive power of their single-layer counterpart.
Meta-Learning with Implicit Processes
This paper presents a novel implicit process-based meta-learning (IPML) algorithm that, in contrast to existing works, explicitly represents each task as a continuous latent vector and models its probabilistic belief within the highly expressive IP framework.
Balancing training time vs. performance with Bayesian Early Pruning
Pruning is an approach to alleviate overparameterization of deep neural networks (DNN) by zeroing out or pruning DNN elements with little to no efficacy at a given task.
Top-$k$ Ranking Bayesian Optimization
This paper presents a novel approach to top-$k$ ranking Bayesian optimization (top-$k$ ranking BO) which is a practical and significant generalization of preferential BO to handle top-$k$ ranking and tie/indifference observations.
An Information-Theoretic Framework for Unifying Active Learning Problems
This paper presents an information-theoretic framework for unifying active learning problems: level set estimation (LSE), Bayesian optimization (BO), and their generalized variant.
Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimization
The problem of inverse reinforcement learning (IRL) is relevant to a variety of tasks including value alignment and robot learning from demonstration.
Variational Bayesian Unlearning
We frame this problem as one of minimizing the Kullback-Leibler divergence between the approximate posterior belief of model parameters after directly unlearning from erased data vs. the exact posterior belief from retraining with remaining data.
Collaborative Machine Learning with Incentive-Aware Model Rewards
This paper proposes to value a party's reward based on Shapley value and information gain on model parameters given its data.
Private Outsourced Bayesian Optimization
This paper presents the private-outsourced-Gaussian process-upper confidence bound (PO-GP-UCB) algorithm, which is the first algorithm for privacy-preserving Bayesian optimization (BO) in the outsourced setting with a provable performance guarantee.
A Unifying Framework of Bilinear LSTMs
This paper presents a novel unifying framework of bilinear LSTMs that can represent and utilize the nonlinear interaction of the input features present in sequence datasets for achieving superior performance over a linear LSTM and yet not incur more parameters to be learned.
Distributed Batch Gaussian Process Optimization
To realize this, we generalize GP-UCB to a new batch variant amenable to a Markov approximation, which can then be naturally formulated as a multi-agent distributed constraint optimization problem in order to fully exploit the efficiency of its state-of-the-art solvers for achieving linear time in the batch size.
Inverse Reinforcement Learning with Locally Consistent Reward Functions
By representing our IRL problem with a probabilistic graphical model, an expectation-maximization (EM) algorithm can be devised to iteratively learn the different reward functions and the stochastic transitions between them in order to jointly improve the likelihood of the expert’s demonstrated trajectories.
