Fiber simplifies RL and population-based methods for distributed training.
problem Challenges in RL and population-based methods, including frequent interaction with simulations and dynamic scaling.
method Introducing Fiber, a scalable distributed computing framework.
result Significantly expands accessibility of large-scale parallel computation.
Population-based learning improves representation of unstructured data.
problem Improving representation of unstructured data.
method Instantiating Lewis signaling games within a population of agents.
result Population-based learning produces better representations than single-agent learning.
New meta-optimizer learns from both point-based and population-based algorithms.
problem Current meta-optimizers are limited in space and unaware of uncertainty.
method Proposes a new meta-optimizer that learns in the space of both point-based and population-based algorithms, targeting a meta-loss function of cumulative regret and entropy.
result Empirical results show superior performance over existing competitors.
PB2 uses probabilistic models to efficiently discover high-performing hyperparameters.
problem Efficiently tuning hyperparameters in reinforcement learning (RL) is computationally expensive and laborious.
method Population-Based Bandits (PB2) uses probabilistic models to guide hyperparameter exploration.
result PB2 discovers high-performing hyperparameter configurations with fewer agents than PBT.
Dynamic meta-learning improves multi-agent communication with natural language.
problem Static population-based approaches struggle with adapting to human partners using natural language.
method Dynamic population-based meta-learning approach.
result Agents outperform all prior work in communicating with seen partners and humans.
Aims to describe neural network training dynamics using two-time-scale models.
problem Lack of a general mathematical description of neural network training.
method Introduces a theoretical framework based on two-time-scale population dynamics.
result Derives selection-mutation equations and effective fitness for hyperparameters.
Despite recent innovations in network architectures and loss functions, training RNNs to learn long-term dependencies remains difficult due to challenges with gradient-based optimisation methods. Inspired by the success of Deep Neuroevolution in reinforcement learning (Such et al. 2017), we explore the use of gradient-…
Current paper addresses topology issues in PBSHM to enable transfer learning.
problem Absence of meaningful topology on graph space hinders rigorous analysis.
method Introduced parametric families of structures, defined open sets, and continuous variation between fibres.
result Enabled rigorous transfer learning in PBSHM by addressing topology issues.
Automates RL with sample-efficient hyperparameter optimization.
problem Challenges in applying deep RL due to hyperparameter sensitivity and inefficiency.
method Population-based AutoRL framework for meta-optimizing RL algorithms and architectures.
result Reduces the number of environment interactions needed for meta-optimization by up to an order of magnitude.
FIRE PBT improves neural network training by focusing on long-term performance.
problem Greedy decision mechanisms in PBT lead to poor long-term performance.
method FIRE PBT uses a fitness metric to encourage long-term performance over short-term improvements.
result FIRE PBT outperforms PBT on ImageNet and matches hand-tuned learning rates.
Operator calculus for population-based optimization provides a unified framework for analyzing convergence of various methods.
problem Convergence analysis of population-based optimization methods
method Introduce an operator calculus for describing composite mean-field algorithms as compositions of elementary operators acting on probability measures.
result Establish a modular Lyapunov principle for certifying exponential decay of state-space Lyapunov function and search errors.
A key challenge in leveraging data augmentation for neural network training is choosing an effective augmentation policy from a large search space of candidate operations. Properly chosen augmentation policies can lead to significant generalization improvements; however, state-of-the-art approaches such as AutoAugment …
In this paper, we will provide an introduction to the derivative-free optimization algorithms which can be potentially applied to train deep learning models. Existing deep learning model training is mostly based on the back propagation algorithm, which updates the model variables layers by layers with the gradient desc…
High-throughput 3D control training system achieves 100,000 FPS.
problem Lack of efficient, single-machine reinforcement learning systems.
method Sample Factory combines asynchronous sampling and off-policy correction.
result Achieves 100,000 FPS on 3D control problems without sacrificing sample efficiency.
Improves exploration in reinforcement learning with diverse population.
problem Lack of diversity in reinforcement learning agents leads to limited exploration.
method Optimizes a population of agents using volume of behavioral manifold and online learning techniques.
result Improves exploration without sacrificing performance.
Graph coloring involves assigning colors to the vertices of a graph such that two vertices linked by an edge receive different colors. Graph coloring problems are general models that are very useful to formulate many relevant applications and, however, are computationally difficult. In this work, a general population-b…
Robust RL improves controller robustness to dynamics variations using adversarial populations.
problem Robustness issues in RL when dynamics are perturbed.
method Adversarial population augmentation to the Robust RL formulation.
result Population-based adversarial approach yields more robust and generalizable policies.
Improved disentanglement of data factors using recursive training.
problem Current unsupervised disentanglement methods are inconsistent and fail to achieve levels of disentanglement seen in supervised approaches.
method Introduced PBT for VAEs, used UDR for heuristic scoring, and developed recursive rPU-VAE approach.
result Recursive training leads to robust disentanglement of data factors across multiple datasets.
While we would like agents that can coordinate with humans, current algorithms such as self-play and population-based training create agents that can coordinate with themselves. Agents that assume their partner to be optimal or similar to them can converge to coordination protocols that fail to understand and be unders…
Study improves engagement prediction in educational videos.
problem Addressing cold-start problem in educational recommenders.
method Introduced VLE dataset with content and engagement features, conducted experiments.
result VLE dataset leads to better engagement prediction models.
ABPS improves RL training efficiency by sharing policies and evolving hyper-params.
problem Data inefficiency in training deep RL models for real-world applications.
method ABPS: adaptive behavior policy sharing; ABPS-PBT: hybridizing ABPS with PBT for evolving hyper-params.
result ABPS achieves superior performance and reduced variance compared to conventional hyper-parameter tuning.
This paper develops a geometric framework for SHM using feature bundles and gauge theories.
problem Defining feature spaces in population-based SHM.
method Introduces feature bundles as sections of vector bundles over structure spaces, and uses Graph Neural Networks for feature assignment.
result Develops a mathematical framework for SHM that incorporates feature spaces and gauge theories.
Study finds RNNs predict STBG better than ARIMA, useful for diabetes patients.
problem Improving short-term blood glucose prediction for diabetes management.
method Investigated Recurrent Neural Networks (RNNs) and compared them to ARIMA for STBG prediction.
result Population-based RNN model outperforms ARIMA across various prediction horizons.
Continuous control tasks in reinforcement learning are important because they provide an important framework for learning in high-dimensional state spaces with deceptive rewards, where the agent can easily become trapped into suboptimal solutions. One way to avoid local optima is to use a population of agents to ensure…
Objectives: Most cancer data sources lack information on metastatic recurrence. Electronic medical records (EMRs) and population-based cancer registries contain complementary information on cancer treatment and outcomes, yet are rarely used synergistically. To enable detection of metastatic breast cancer (MBC), we appl…
P3BO optimizes biological sequence design by combining multiple methods.
problem Variability in performance of black-box optimization methods for biological sequence design.
method Population-Based Black-Box Optimization (P3BO) that samples sequences from an ensemble of methods, weighting by past performance.
result P3BO outperforms individual methods, proposing higher quality and more diverse sequences.
Counterfactual learning from observational data involves learning a classifier on an entire population based on data that is observed conditioned on a selection policy. This work considers this problem in an active setting, where the learner additionally has access to unlabeled examples and can choose to get a subset o…
Researchers developed a generic model to account for structural variability in SHM.
problem Variability in natural frequency due to operational and environmental conditions limits SHM technologies.
method An overlapping mixture of Gaussian processes (OMGP) was used to generate a generic representation of normal condition.
result The OMGP model provided a generic representation (form) to characterise the normal condition of structures.
The performance of policy gradient methods is sensitive to hyperparameter settings that must be tuned for any new application. Widely used grid search methods for tuning hyperparameters are sample inefficient and computationally expensive. More advanced methods like Population Based Training that learn optimal schedule…
Clinical diagnostic decision making and population-based studies often rely on multi-modal data which is noisy and incomplete. Recently, several works proposed geometric deep learning approaches to solve disease classification, by modeling patients as nodes in a graph, along with graph signal processing of multi-modal …
Developed a cost and revenue model for HEMS to estimate breakeven transport volumes under different reimbursement and labor cost assumptions.
problem Estimating breakeven transport volumes for HEMS under varying reimbursement and labor cost assumptions.
method Developed a two-part model: cost framework and actuarial revenue model using healthcare encounter data and payer reimbursement rates.
result Estimated breakeven transport volumes under different reimbursement and labor cost assumptions.
Optimizes sampling in continuous domains by adjusting search distribution.
problem Improving sampling efficiency in continuous domains.
method Analyzes and refines the search distribution based on population size and dimension.
result Explicit values for reshaping the search distribution are provided.
The paper investigates how supervised learning and self-play improve sample efficiency in teaching AI to communicate.
problem Improving sample efficiency in training AI to use natural language.
method Investigates the relationship between supervised learning and self-play, introduces supervised self-play (S2P).
result First training agents via supervised learning followed by self-play outperforms self-play followed by supervised learning.
Enhances inverse design optimization with machine learning and reduced fidelity simulations.
problem Limited compute resources in inverse design optimization.
method Synergy of multi-fidelity simulations, machine learning, and search space reduction.
result Significant computational resource savings and improved optimization performance.
In this paper, we will provide an introduction to the derivative-free optimization algorithms which can be potentially applied to train deep learning models. Existing deep learning model training is mostly based on the back propagation algorithm, which updates the model variables layers by layers with the gradient desc…
GNMC reduces XCSF population size while preserving function approximation and policy accuracy.
problem Population bloat in XCSF compaction.
method Introduced GNMC, a novel compaction algorithm.
result GNMC reduces population size significantly without compromising function approximation or policy accuracy.
There is emerging interest in performing regression between distributions. In contrast to prediction on single instances, these machine learning methods can be useful for population-based studies or on problems that are inherently statistical in nature. The recently proposed distribution regression network (DRN) has sh…
Deep Reinforcement Learning (DRL) algorithms have been successfully applied to a range of challenging control tasks. However, these methods typically suffer from three core difficulties: temporal credit assignment with sparse rewards, lack of effective exploration, and brittle convergence properties that are extremely …
Epidemiology simulations have become a fundamental tool in the fight against the epidemics of various infectious diseases like AIDS and malaria. However, the complicated and stochastic nature of these simulators can mean their output is difficult to interpret, which reduces their usefulness to policymakers. In this pap…
Hybridizes CEM and gradient descent for efficient model-predictive control.
problem Efficiently planning optimal action sequences in high-dimensional spaces.
method Interleaves Cross-Entropy Method (CEM) and gradient descent steps.
result Faster convergence and avoidance of local optima compared to CEM.
Proposes a new framework to manage venture capital portfolio risk by focusing on deal-level correlations.
problem Managing venture capital portfolio risk, especially extreme outcomes.
method Gaussian-copula-based framework that learns deal-level dependence from observed joint success frequencies.
result Correlation amplifies extreme upside outcomes, shifting portfolio distribution toward heavier right tails.
This paper is concerned with a recently developed paradigm for population-based optimization, termed particle filter optimization (PFO). This paradigm is attractive in terms of coherence in theory and easiness in mathematical analysis and interpretation. Current PFO algorithms only work for single-objective optimizatio…
The paper proposes a new method for comparing logistic regression models across different populations.
problem Comparing logistic regression models across sub-populations can lead to misleading results.
method Develops a cascading set of equivalence tests for logistic regression models, addressing coding, predictions, and overall accuracy.
result Equivalence testing incentivizes accurate inference and avoids perverse incentives from significance tests.
Artificial neural network (ANN) provides superior accuracy for nonlinear alternating current (AC) state estimation (SE) in smart grid over traditional methods. However, research has discovered that ANN could be easily fooled by adversarial examples. In this paper, we initiate a new study of adversarial false data injec…
Paper proposes EMO-based AE generation for black-box settings.
problem Designing robust adversarial examples for black-box models.
method Evolutionary Multi-objective Optimization (EMO) for generating various types of adversarial examples.
result EMO-based method generates AEs that are robust and applicable to high-resolution images.
Deep neural networks classify T2D from retinal images with high accuracy.
problem Detecting early-stage Type 2 Diabetes from retinal images.
method Employed deep neural networks and multi-target learning to differentiate T2D from healthy individuals.
result Classification performance improved to AUC = 0.758 [±0.003] using images from both eyes. We propose a population-based Evolutionary Stochastic Gradient Descent (ESGD) framework for optimizing deep neural networks. ESGD combines SGD and gradient-free evolutionary algorithms as complementary algorithms in one framework in which the optimization alternates between the SGD step and evolution step to improve th…
Bayesian method models multivalued power data from wind farms.
problem Accurate modeling of power curves with multivalued relationships.
method Overlapping mixture of probabilistic regression models.
result Model accurately represents practical power data.