Suggester	Paper
George De Ath	Random tessellation forests
George De Ath	Approximate Cross-Validation in High Dimensions with Guarantees
George De Ath	Differentiation of Blackbox Combinatorial Solvers
George De Ath	The Implicit Regularization of Ordinary Least Squares Ensembles
George De Ath	Near-linear Time Gaussian Process Optimization with Adaptive Batching and Resparsification
George De Ath	Predicting the outputs of finite networks trained with noisy gradients
George De Ath	Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimization
George De Ath	Semi-supervised Embedding Learning for High-dimensional Bayesian Optimization
George De Ath	Gradient Estimation with Stochastic Softmax Tricks
George De Ath	Optimal Lottery Tickets via SubsetSum: Logarithmic Over-Parameterization is Sufficient
George De Ath	NGBoost: Natural Gradient Boosting for Probabilistic Prediction
George De Ath	Explaining The Behavior Of Black-Box Prediction Algorithms With Causal Learning
George De Ath	Uncertainty quantification using martingales for misspecified Gaussian processes
George De Ath	Latent variable modeling with random features
George De Ath	Discovering Symbolic Models from Deep Learning with Inductive Biases
George De Ath	Survey of machine-learning experimental methods atNeurIPS2019 and ICLR2020
Tinkle Chugh	Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search
George De Ath	A Unifying Perspective on Neighbor Embeddings along the Attraction-Repulsion Spectrum
George De Ath	Meta-Surrogate Benchmarking for Hyperparameter Optimization
George De Ath	Optimizer Benchmarking Needs to Account for Hyperparameter Tuning
George De Ath	Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations
George De Ath	Reverse engineering learned optimizers reveals known and novel mechanisms
George De Ath	Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search
George De Ath	Mastering Atari, Go, chess and shogi by planning with a learned model
George De Ath	A Tutorial on Sparse Gaussian Processes and Variational Inference
George De Ath	Good practices for Bayesian Optimization of high dimensional structured spaces
George De Ath	Expressive yet Tractable Bayesian Deep Learning via Subnetwork Inference
George De Ath	GIBBON: General-purpose Information-Based BayesianOptimisatioN
George De Ath	Accounting for Variance in Machine Learning Benchmarks
Melike Karatas	Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling
George De Ath	Deep Evidential Regression
George De Ath	Sparse Uncertainty Representation in Deep Learning with Inducing Weights
George De Ath	Convergence Guarantees for Gaussian Process Means With Misspecified Likelihoods and Smoothness
George De Ath	Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization
George De Ath	LocoProp: Enhancing BackProp via Local Loss Optimization
Richard Everson	Sharpness-aware Minimization for Efficiently Improving Generalization
George De Ath	Kernel Identification Through Transformers
George De Ath	What can linear interpolation of neural network loss landscapes tell us?
George De Ath	Bayesian Optimization with High-Dimensional Outputs
George De Ath	Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs
George De Ath	Pretrained Transformers as Universal Computation Engines
George De Ath	Gradient-based Hyperparameter Optimization Over Long Horizons
George De Ath	Stochastic Contrastive Learning
George De Ath	Stochastic Training is Not Necessary for Generalization
George De Ath	Deep Neural Networks and Tabular Data: A Survey
George De Ath	What's a good imputation to predict with missing values?
George De Ath	Revisiting Design Choices in Model-Based Offline Reinforcement Learning
George De Ath	SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training
George De Ath	Random Hypervolume Scalarizations for Provable Multi-Objective Black Box Optimization
George De Ath	High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning
George De Ath	Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
George De Ath	Correspondence between neuroevolution and gradient descent
George De Ath	Gradients are Not All You Need
George De Ath	Bayesian Modeling and Uncertainty Quantification for Learning to Optimize: What, Why, and How
George De Ath	Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
George De Ath	Do We Really Need Deep Learning Models for Time Series Forecasting?
George De Ath	Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer
George De Ath	Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
George De Ath	A Modern Self-Referential Weight Matrix That Learns to Modify Itself
George De Ath	Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations
George De Ath	The Distributed Information Bottleneck reveals the explanatory structure of complex systems
George De Ath	Random Features for Kernel Approximation: A Survey on Algorithms, Theory, and Beyond
George De Ath	Learning Strides in Convolutional Neural Networks
George De Ath	Comparing Distributions by Measuring Differences that Affect Decision Making
George De Ath	Machine Learning State-of-the-Art with Uncertainties
George De Ath	It's DONE: Direct ONE-shot learning without training optimization
George De Ath	A Learning-based Innovized Progress Operator for Faster Convergence in Evolutionary Multi-objective Optimization
George De Ath	Sharpness-Aware Training for Free
George De Ath	Transfer Learning with Deep Tabular Models
George De Ath	(Certified!!) Adversarial Robustness for Free!
George De Ath	Neural Diffusion Processes
George De Ath	Sample-Efficient Optimisation with Probabilistic Transformer Surrogates
George De Ath	Learning Iterative Reasoning through Energy Minimization
George De Ath	Understanding Dataset Difficulty with V-Usable Information
George De Ath	Formal Algorithms for Transformers
Tinkle Chugh	Bayesian Optimization over Discrete and Mixed Spaces via Probabilistic Reparameterization
Tinkle Chugh	A Parallel Technique for Multi-objective Bayesian Global Optimization: Using a Batch Selection of Probability of Improvement
George De Ath	AutoML Loss Landscapes
George De Ath	Visualizing high-dimensional loss landscapes with Hessian directions
George De Ath	Transformers are Sample Efficient World Models
George De Ath	Well-tuned Simple Nets Excel on Tabular Datasets
George De Ath	Git Re-Basin: Merging Models modulo Permutation Symmetries
George De Ath	Diffusion Models: A Comprehensive Survey of Methods and Applications
George De Ath	Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Prior
George De Ath	What Can Transformers Learn In-Context? A Case Study of Simple Function Classes
George De Ath	Ensemble-based gradient inference for particle methods in optimization and sampling
George De Ath	Protein structure generation via folding diffusion
George De Ath	Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics
George De Ath	Learning to Learn with Generative Models of Neural Network Checkpoints
George De Ath	Joint Embedding Self-Supervised Learning in the Kernel Regime
George De Ath	Batch Normalization Explained
George De Ath	An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning
George De Ath	Efficient Non-Parametric Optimizer Search for Diverse Tasks
George De Ath	TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second
George De Ath	Efficient Transformers: A Survey (v2)
George De Ath	Foundation Transformers
George De Ath	How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization
George De Ath	Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations
George De Ath	Bayesian Optimization with Conformal Coverage Guarantees
George De Ath	Targeted active learning for probabilistic models
George De Ath	Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation
George De Ath	Multi-Objective GFlowNets
George De Ath	Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation
George De Ath	HesScale: Scalable Computation of Hessian Diagonals
George De Ath	Optimisation & Generalisation in Networks of Neurons
George De Ath	Convexifying Transformers: Improving optimization and understanding of transformer networks
George De Ath	Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities
Tinkle Chugh	GAUCHE: A Library for Gaussian Processes in Chemistry
George De Ath	Information-Theoretic Safe Exploration with Gaussian Processes
George De Ath	On the role of Model Uncertainties in Bayesian Optimization
George De Ath	A Succinct Summary of Reinforcement Learning
George De Ath	The Forward-Forward Algorithm: Some Preliminary Investigations
George De Ath	A Comprehensive Survey to Dataset Distillation
George De Ath	ExcelFormer: A Neural Network Surpassing GBDTs on Tabular Data
Tinkle Chugh	SnAKe: Bayesian Optimization with Pathwise Exploration
George De Ath	A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT
Tinkle Chugh	Multi-Objective Learning to Predict Pareto Fronts Using Hypervolume Maximization
George De Ath	Transformer models: an introduction and catalog
George De Ath	Efficiently Modeling Long Sequences with Structured State Spaces
George De Ath	Adaptive Experimentation at Scale: Bayesian Algorithms for Flexible Batches
George De Ath	Effectively Modeling Time Series with Simple Discrete State Spaces
George De Ath	Self-Distillation for Gaussian Process Regression and Classification
Tinkle Chugh	Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle
George De Ath	Prediction-oriented Bayesian active learning
George De Ath	A Study of Bayesian Neural Network Surrogates for Bayesian Optimization
Tinkle Chugh	Finding Robust Solutions for Many-Objective Optimization Using NSGA-III
Tinkle Chugh	Visualization-aided multi-criteria decision-making using interpretable self-organizing maps

Previously-discussed Papers

Suggester	Paper
George De Ath	Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits
George De Ath	BOHB: Robust and Efficient Hyperparameter Optimization at Scale
George De Ath	Meta-Learning Acquisition Functions for Transfer Learning in Bayesian Optimization
Tinkle Chugh	Multifactorial Evolution: Toward Evolutionary Multitasking
Richard Everson	You Only Train Once: Loss-Conditional Training of Deep Networks
Tinkle Chugh	Local optima networks for continuous fitness landscapes
Tinkle Chugh	ConBO: Conditional Bayesian Optimization
George De Ath	Knowing The What But Not The Where in Bayesian Optimization
Tinkle Chugh	BOSH: Bayesian Optimization by Sampling Hierarchically
Matt Johns	Adaptive augmented evolutionary intelligence for the design of water distribution networks
Jonathan Fieldsend	Data structures for non-dominated sets: implementations and empirical assessment of two decades of advances
Clodomir Santana	An approach to assess swarm intelligence algorithms based on complex networks
Mariana Macedo	Breast cancer diagnosis using thermal image analysis: an approach based on deep learning and multi-objective binary fish school search for optimized feature selection
Fabrizio Costa	Fair Bayesian Optimization
George De Ath	Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs
Melike Karatas	Multi-layer local optima networks for the analysis of advanced local search-based algorithms
Richard Everson	A Very Simple Safe-Bayesian Random Forest
George De Ath	Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves
Tinkle Chugh	Controllable Pareto Multi-Task Learning
George De Ath	BORE: Bayesian Optimization by Density-Ratio Estimation
George De Ath	Preferential Batch Bayesian Optimization
Tinkle Chugh	Multi-modal Multi-objective Optimization: Problem Analysis and Case Studies
George De Ath	On Empirical Comparisons of Optimizers for Deep Learning
Tinkle Chugh	Bayesian Optimization with Approximate Set Kernels
Jonathan Fieldsend	On Sequential Online Archiving of Objective Vectors
Richard Everson	Reconciling modern machine-learning practice and the classical bias–variance trade-off
Gregory Daly	Intelligent Process Control – Overcoming the challenge of controlling the processing environment with deep learning
Alma Rahat	Supporting Policy Decisions in the Covid-19 Pandemic
Melike Karatas	Visualizing the Loss Landscape of Neural Nets
Richard Everson	NOMU: Neural Optimization-based Model Uncertainty
Tinkle Chugh	Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information
Tim Dodwell	Analyzing Inverse Problems with Invertible Neural Networks
George De Ath	Conservative Objective Models for Effective Offline Model-Based Optimization
Andy Corbett	Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
Tinkle Chugh	Combining Gaussian Processes with Neural Networks for Active Learning in Optimization
George De Ath	Laplace Redux -- Effortless Bayesian Deep Learning
Melike Karatas	Search trajectory networks: A tool for analysing and visualising the behaviour of metaheuristics
Andrew Corbett	Imbedding Deep Neural Networks
Richard Everson	TabNet: Attentive Interpretable Tabular Learning
Michael Dunne	Probabilistic sensitivity analysis of complex models: a Bayesian approach
Greg Daly	A Universal Law of Robustness via Isoperimetry
George De Ath	Transformers Can Do Bayesian Inference
Abhra Chaudhuri	Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
George De Ath	Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective
Tinkle Chugh	Scalable Thompson Sampling using Sparse Gaussian Process Models
George De Ath	Balanced MSE for Imbalanced Visual Regression
Andy Corbett	GParareal: A time-parallel ODE solver using Gaussian process emulation
George De Ath	Learning the Pareto Front with Hypernetworks
George De Ath	Towards Learning Universal Hyperparameter Optimizers with Transformers
George De Ath	Sequential adaptive design for emulating costly computer codes
George De Ath	Why do tree-based models still outperform deep learning on tabular data?
Ayah Helal	Change Detection for Local Explainability in Evolving Data Streams
George De Ath	VeLO: Training Versatile Learned Optimizers by Scaling Up
Richard Everson	AutoML-Zero: Evolving Machine Learning Algorithms From Scratch
Tinkle Chugh	A Bayesian Active Learning Approach to Comparative Judgement