Search Results for author:
Found 37 papers, 17 papers with code
Self-Supervision Improves Diffusion Models for Tabular Data Imputation
Additionally, the sparsity inherent in tabular data poses challenges for diffusion models in accurately modeling the data manifold, impacting the robustness of these models for data imputation.
Rejection via Learning Density Ratios
Instead, we propose a different distributional perspective, where we seek to find an idealized data distribution which maximizes a pretrained model's performance.
High-dimensional Bayesian Optimization via Covariance Matrix Adaptation Strategy
To address this issue, a promising solution is to use a local search strategy that partitions the search domain into local regions with high likelihood of containing the global optimum, and then use BO to optimize the objective function within these regions.
Provably Efficient Bayesian Optimization with Unknown Gaussian Process Hyperparameter Estimation
To address this issue, we propose a new BO method that can sub-linearly converge to the objective function's global optimum even when the true GP hyperparameters are unknown in advance and need to be estimated from the observed data.
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.
Zero-shot Object Counting
By applying this model to all the candidate patches, we can select the most suitable patches as exemplars for counting.
Ranked #7 on
Zero-Shot Counting
on FSC147
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.
Confident Sinkhorn Allocation for Pseudo-Labeling
CSA outperforms the current state-of-the-art in this practically important area of semi-supervised learning.
Retrieval Augmented Classification for Long-Tail Visual Recognition
We introduce Retrieval Augmented Classification (RAC), a generic approach to augmenting standard image classification pipelines with an explicit retrieval module.
Ranked #6 on
Long-tail Learning
on iNaturalist 2018
Automated Reinforcement Learning (AutoRL): A Survey and Open Problems
The combination of Reinforcement Learning (RL) with deep learning has led to a series of impressive feats, with many believing (deep) RL provides a path towards generally capable agents.
Gaussian Process Sampling and Optimization with Approximate Upper and Lower Bounds
More specifically, we propose the first use of such bounds to improve Gaussian process (GP) posterior sampling and Bayesian optimization (BO).
Bayesian Topic Regression for Causal Inference
To this end, we combine a supervised Bayesian topic model with a Bayesian regression framework and perform supervised representation learning for the text features jointly with the regression parameter training, respecting the Frisch-Waugh-Lovell theorem.
Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL
Despite a series of recent successes in reinforcement learning (RL), many RL algorithms remain sensitive to hyperparameters.
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.
A Vietnamese Dataset for Evaluating Machine Reading Comprehension
Due to the lack of benchmark datasets for Vietnamese, we present the Vietnamese Question Answering Dataset (UIT-ViQuAD), a new dataset for the low-resource language as Vietnamese to evaluate MRC models.
Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective
Achieving the full promise of the Thermodynamic Variational Objective (TVO), a recently proposed variational lower bound on the log evidence involving a one-dimensional Riemann integral approximation, requires choosing a "schedule" of sorted discretization points.
Optimal Transport Kernels for Sequential and Parallel Neural Architecture Search
Building upon tree-Wasserstein (TW), which is a negative definite variant of OT, we develop a novel discrepancy for neural architectures, and demonstrate it within a Gaussian process surrogate model for the sequential NAS settings.
Incorporating Expert Prior Knowledge into Experimental Design via Posterior Sampling
Again, it is unknown how to incorporate the expert prior knowledge about the global optimum into Bayesian optimization process.
Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits
A recent solution to this problem is Population Based Training (PBT) which updates both weights and hyperparameters in a single training run of a population of agents.
Hierarchical Indian Buffet Neural Networks for Bayesian Continual Learning
We place an Indian Buffet process (IBP) prior over the structure of a Bayesian Neural Network (BNN), thus allowing the complexity of the BNN to increase and decrease automatically.
Bayesian Optimization for Iterative Learning
We demonstrate the efficiency of our algorithm by tuning hyperparameters for the training of deep reinforcement learning agents and convolutional neural networks.
Accelerating Experimental Design by Incorporating Experimenter Hunches
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.
Bayesian Optimisation over Multiple Continuous and Categorical Inputs
Efficient optimisation of black-box problems that comprise both continuous and categorical inputs is important, yet poses significant challenges.
Knowing The What But Not The Where in Bayesian Optimization
In this paper, we consider a new setting in BO in which the knowledge of the optimum output f* is available.
Algorithmic Assurance: An Active Approach to Algorithmic Testing using Bayesian Optimisation
We address this problem by proposing an efficient framework for algorithmic testing.
Practical Batch Bayesian Optimization for Less Expensive Functions
Bayesian optimization (BO) and its batch extensions are successful for optimizing expensive black-box functions.
High Dimensional Bayesian Optimization Using Dropout
Scaling Bayesian optimization to high dimensions is challenging task as the global optimization of high-dimensional acquisition function can be expensive and often infeasible.
A+D Net: Training a Shadow Detector with Adversarial Shadow Attenuation
The A-Net modifies the original training images constrained by a simplified physical shadow model and is focused on fooling the D-Net's shadow predictions.
Shadow Detection With Conditional Generative Adversarial Networks
We introduce scGAN, a novel extension of conditional Generative Adversarial Networks (GAN) tailored for the challenging problem of shadow detection in images.
Ranked #6 on
RGB Salient Object Detection
on ISTD
High Dimensional Bayesian Optimization with Elastic Gaussian Process
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.
Sparse Autoencoder for Unsupervised Nucleus Detection and Representation in Histopathology Images
In this work, we propose a sparse Convolutional Autoencoder (CAE) for fully unsupervised, simultaneous nucleus detection and feature extraction in histopathology tissue images.
Geodesic Distance Histogram Feature for Video Segmentation
This paper proposes a geodesic-distance-based feature that encodes global information for improved video segmentation algorithms.
Ranked #1 on
Video Segmentation
on SegTrack v2
Budgeted Batch Bayesian Optimization With Unknown Batch Sizes
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.
Dual Space Gradient Descent for Online Learning
However, this approach still suffers from a serious shortcoming as it needs to use a high dimensional random feature space to achieve a sufficiently accurate kernel approximation.
Scalable Semi-supervised Learning with Graph-based Kernel Machine
Acquiring labels are often costly, whereas unlabeled data are usually easy to obtain in modern machine learning applications.
Approximation Vector Machines for Large-scale Online Learning
One of the most challenging problems in kernel online learning is to bound the model size and to promote the model sparsity.
Bayesian Nonparametric Multilevel Clustering with Group-Level Contexts
We present a Bayesian nonparametric framework for multilevel clustering which utilizes group-level context information to simultaneously discover low-dimensional structures of the group contents and partitions groups into clusters.
