Search Results for author:
Found 25 papers, 15 papers with code
UQE: A Query Engine for Unstructured Databases
This engine accepts queries in a Universal Query Language (UQL), a dialect of SQL that provides full natural language flexibility in specifying conditions and operators.
Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization
Automatic prompt optimization (APO) methods are designed to automate this and can be broadly categorized into those targeting instructions (instruction optimization, IO) vs. those targeting exemplars (exemplar selection, ES).
Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments
Motivated by this phenomenon, we propose an automatic Zero-shot Evaluation-oriented Prompt Optimization framework, ZEPO, which aims to produce fairer preference decisions and improve the alignment of LLM evaluators with human judgments.
Bayesian Optimization of Functions over Node Subsets in Graphs
We address the problem of optimizing over functions defined on node subsets in a graph.
Survival of the Most Influential Prompts: Efficient Black-Box Prompt Search via Clustering and Pruning
Prompt-based learning has been an effective paradigm for large pretrained language models (LLM), enabling few-shot or even zero-shot learning.
Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering
Prompting and in-context learning (ICL) have become efficient learning paradigms for large language models (LLMs).
Adaptive Batch Sizes for Active Learning A Probabilistic Numerics Approach
Active learning parallelization is widely used, but typically relies on fixing the batch size throughout experimentation.
Universal Self-Adaptive Prompting
A hallmark of modern large language models (LLMs) is their impressive general zero-shot and few-shot abilities, often elicited through in-context learning (ICL) via prompting.
Better Zero-Shot Reasoning with Self-Adaptive Prompting
Modern large language models (LLMs) have demonstrated impressive capabilities at sophisticated tasks, often through step-by-step reasoning similar to humans.
SimSC: A Simple Framework for Semantic Correspondence with Temperature Learning
This module is trained together with the backbone and the temperature is updated online.
Working Memory Capacity of ChatGPT: An Empirical Study
Working memory is a critical aspect of both human intelligence and artificial intelligence, serving as a workspace for the temporary storage and manipulation of information.
Bayesian Quadrature for Neural Ensemble Search
Ensembling can improve the performance of Neural Networks, but existing approaches struggle when the architecture likelihood surface has dispersed, narrow peaks.
AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning
Large pretrained language models are widely used in downstream NLP tasks via task-specific fine-tuning, but such procedures can be costly.
Bayesian Optimization over Discrete and Mixed Spaces via Probabilistic Reparameterization
We prove that under suitable reparameterizations, the BO policy that maximizes the probabilistic objective is the same as that which maximizes the AF, and therefore, PR enjoys the same regret bounds as the original BO policy using the underlying AF.
Bayesian Generational Population-Based Training
Leveraging the new highly parallelizable Brax physics engine, we show that these innovations lead to large performance gains, significantly outperforming the tuned baseline while learning entire configurations on the fly.
On Redundancy and Diversity in Cell-based Neural Architecture Search
Searching for the architecture cells is a dominant paradigm in NAS.
Adversarial Attacks on Graph Classifiers via Bayesian Optimisation
While the majority of the literature focuses on such vulnerability in node-level classification tasks, little effort has been dedicated to analysing adversarial attacks on graph-level classification, an important problem with numerous real-life applications such as biochemistry and social network analysis.
BOiLS: Bayesian Optimisation for Logic Synthesis
Optimising the quality-of-results (QoR) of circuits during logic synthesis is a formidable challenge necessitating the exploration of exponentially sized search spaces.
Approximate Neural Architecture Search via Operation Distribution Learning
The standard paradigm in Neural Architecture Search (NAS) is to search for a fully deterministic architecture with specific operations and connections.
Adversarial Attacks on Graph Classification via Bayesian Optimisation
While the majority of the literature focuses on such vulnerability in node-level classification tasks, little effort has been dedicated to analysing adversarial attacks on graph-level classification, an important problem with numerous real-life applications such as biochemistry and social network analysis.
Attacking Graph Classification via Bayesian Optimisation
Graph neural networks have been shown to be vulnerable to adversarial attacks.
Think Global and Act Local: Bayesian Optimisation over High-Dimensional Categorical and Mixed Search Spaces
High-dimensional black-box optimisation remains an important yet notoriously challenging problem.
Interpretable Neural Architecture Search via Bayesian Optimisation with Weisfeiler-Lehman Kernels
Our method optimises the architecture in a highly data-efficient manner: it is capable of capturing the topological structures of the architectures and is scalable to large graphs, thus making the high-dimensional and graph-like search spaces amenable to BO.
Iterative Averaging in the Quest for Best Test Error
We analyse and explain the increased generalisation performance of iterate averaging using a Gaussian process perturbation model between the true and batch risk surface on the high dimensional quadratic.
Deep Curvature Suite
We present MLRG Deep Curvature suite, a PyTorch-based, open-source package for analysis and visualisation of neural network curvature and loss landscape.
