evo-RL combines evolutionary computation with reinforcement learning for better adaptability.
problem Improving reinforcement learning algorithms' adaptability and performance in environments with rewardless states.
method Embedding reinforcement learning in an evolutionary cycle, distinguishing instinctive from learnable behavior.
result evo-RL leads to state-of-the-art performance on OpenAI Gym control problems with rewardless states.
Momentum speeds up evolutionary processes in machine learning.
problem Accelerating convergence in evolutionary dynamics.
method Combining momentum from machine learning with evolutionary dynamics using information divergences as Lyapunov functions.
result Momentum accelerates convergence of evolutionary dynamics, including the replicator equation and Euclidean gradient descent.
New algorithm improves game learning with randomised optimism.
problem Learning in matrix games with unknown payoffs and bandit feedback.
method Integrates evolutionary algorithms into bandit framework for randomised optimism.
result Achieves sublinear regret, outperforming classical methods.
Evolutionary Strategies optimize hyper-parameters for off-policy learning.
problem Hyper-parameter sensitivity in off-policy learning.
method Application of Evolutionary Strategies for online hyper-parameter tuning.
result Our method outperforms state-of-the-art baselines.
Novel evolutionary strategy solves stochastic constrained optimization problems.
problem Optimizing objective functions with stochastic constraints in reinforcement learning.
method Design of a novel optimization algorithm with a sufficient decrease mechanism for stochastic constrained problems.
result Demonstrated convergence of the algorithm on control tasks and constrained optimization problems.
CoNES optimizes blackbox functions using convex optimization and information geometry.
problem Optimizing high-dimensional blackbox functions efficiently.
method Formulated as a convex program that adapts evolutionary strategies gradient estimates.
result Vastly outperforms conventional blackbox optimization methods on benchmarks and MuJoCo tasks.
Evolution and learning are two of the fundamental mechanisms by which life adapts in order to survive and to transcend limitations. These biological phenomena inspired successful computational methods such as evolutionary algorithms and deep learning. Evolution relies on random mutations and on random genetic recombina…
Neural Architecture Search has shown potential to automate the design of neural networks. Deep Reinforcement Learning based agents can learn complex architectural patterns, as well as explore a vast and compositional search space. On the other hand, evolutionary algorithms offer higher sample efficiency, which is criti…
Many cooperative multiagent reinforcement learning environments provide agents with a sparse team-based reward, as well as a dense agent-specific reward that incentivizes learning basic skills. Training policies solely on the team-based reward is often difficult due to its sparsity. Furthermore, relying solely on the a…
Proposes Genetic Thompson Sampling for multi-armed bandits, improving performance in nonstationary settings.
problem Improving sequential decision making tasks of online learning agents using multi-armed bandits.
method Integrates genetic principles into Thompson Sampling for multi-armed bandits.
result Significantly outperforms baselines in nonstationary settings.
Simplicial learning improves classification by generating compact sparse representations.
problem Difficulty in distinguishing classes on the same subspace.
method Evolutionary simplicial learning approach to sparse representations.
result Evolutionary simplicial learning outperforms other methods in multi-class classification.
A method to control results of gradient descent unsupervised learning in a deep neural network by using evolutionary algorithm is proposed. To process crossover of unsupervisedly trained models, the algorithm evaluates pointwise fitness of individual nodes in neural network. Labeled training data is randomly sampled an…
New research connects evolutionary dynamics to Bayesian learning.
problem Connecting evolutionary biology and Bayesian learning.
method Rigorous mathematical proof using Kushner-Stratonovich equation and gradient flows.
result Discrete time filtering equations converge to Stratonovich interpretation of Kushner-Stratonovich equation.
A co-evolutionary approach for Heston model calibration reduces overfitting with diverse datasets.
problem Overfitting and lack of generalization in Heston model calibration.
method Coupling a genetic algorithm with an evolving neural inverse map, using both GA-history sampling and Latin hypercube sampling.
result Diverse datasets improve out-of-sample stability and calibration accuracy.
EPC curriculum improves MARL performance as agent population grows.
problem Challenges in learning good policies for large multi-agent systems.
method Evolutionary Population Curriculum (EPC) for scaling MARL.
result EPC consistently outperforms baselines as agent population increases.
Many applications in machine learning require optimizing a function whose true gradient is unknown, but where surrogate gradient information (directions that may be correlated with, but not necessarily identical to, the true gradient) is available instead. This arises when an approximate gradient is easier to compute t…
Combines variational and evolutionary optimization for generative models.
problem Optimizing generative models with discrete latent variables.
method Truncated posteriors as variational distributions, evolutionary algorithms applied to variational parameters.
result Evolutionary algorithms effectively optimize variational bounds for generative models.
VisEvol uses evolutionary optimization to find optimal hyperparameters for machine learning models.
problem Finding the best hyperparameters for complex machine learning models is computationally intensive and challenging.
method VisEvol employs evolutionary optimization, storing performant models and improving others through crossover and mutation processes.
result VisEvol generates a voting ensemble of models with improved predictive performance.
Time series prediction with deep learning methods, especially long short-term memory neural networks (LSTMs), have scored significant achievements in recent years. Despite the fact that the LSTMs can help to capture long-term dependencies, its ability to pay different degree of attention on sub-window feature within mu…
New method embeds phylogenetic trees for clustering, recovering evolutionary relationships.
problem Lack of a meaningful way to embed phylogenetic trees into a vector space.
method Split-weight embedding to fit clustering algorithms to phylogenetic trees.
result Split-weight embedding recovers meaningful evolutionary relationships in simulated and real data.
Evolutionary methods improve understanding of LLMs and their relationships.
problem Improving understanding of LLMs and their relationships.
method Relating weights to genotypes and output text to phenotypes using evolutionary methods.
result Estimated evolutionary trees reliably recover the topology of the ground-truth training tree.
In many practical applications of clustering, the objects to be clustered evolve over time, and a clustering result is desired at each time step. In such applications, evolutionary clustering typically outperforms traditional static clustering by producing clustering results that reflect long-term trends while being ro…
Framework improves self-play for cooperative multi-agent learning.
problem Evolutionary learning converges to bad local optima in multi-agent RL.
method Add imaginary rewards using peer prediction method to elicit truthful signals.
result State-of-the-art performance in predator prey, traffic junction and StarCraft tasks.
A real-time federated neural architecture search approach reduces costs and improves performance.
problem High communication and computational demands in federated learning for large models.
method Evolutionary approach with double-sampling technique to optimize model performance and reduce costs.
result Effective real-time federated neural architecture search for deep models on edge devices.
LR-EDNN reduces PDE solver complexity by limiting network weights to low-rank subspace.
problem Efficiently solving time-dependent PDEs with deep neural networks.
method Low-rank constraint on network weights using SVD for efficient parameter updates.
result LR-EDNN achieves comparable accuracy to full EDNN with fewer parameters and lower cost.
Protein contacts contain important information for protein structure and functional study, but contact prediction from sequence remains very challenging. Both evolutionary coupling (EC) analysis and supervised machine learning methods are developed to predict contacts, making use of different types of information, resp…
ESPD improves learning efficiency in sparse reward reinforcement learning.
problem Sparse reward reinforcement learning challenges.
method Evolutionary Stochastic Policy Distillation (ESPD) based on drifted random walk insight.
result High learning efficiency demonstrated in MuJoCo robotics control suite experiments.
We define Lie algebroids over infinite jet spaces and establish their equivalent representation through homological evolutionary vector fields.
A new method simulates large, diverse populations of learning agents evolving in games.
problem Limited scalability and efficiency of Multi-Agent Reinforcement Learning.
method Parallelizable implementation of Policy Gradient and Opponent-Learning Awareness for evolutionary simulations.
result Simulated large, diverse populations of learning agents evolve under various strategies.
In this note, we extend an evolutionary stochastic portfolio optimization framework to include probabilistic constraints. Both the stochastic programming-based modeling environment as well as the evolutionary optimization environment are ideally suited for an integration of various types of probabilistic constraints. W…
A new method estimates protein evolutionary fields and couplings from alignments.
problem Estimating evolutionary fields and couplings from protein sequence alignments.
method Boltzmann machine with parallel, persistent Markov chain Monte Carlo method.
result Improved precision in predicting contact residue pairs.
Enhances Bayesian learning with rule-based evolutionary techniques.
problem Improving Bayesian inference with expert knowledge and data patterns.
method Combines Bayesian inference with rule-based systems and grammatical evolution.
result Automatically derives rules from data, improving point predictions and uncertainty quantification.
EKH adds metrics to knot theory, enabling more detailed analysis.
problem Lack of quantitative data in knot theory.
method Integrates metric into knot theory with evolutionary Khovanov homology (EKH).
result EKH reveals non-trivial knot invariants at appropriate scales.
Evolutionary methods improve neural network loss functions, reducing overfitting.
problem Improving neural network performance and preventing overfitting.
method Evolutionary computation to optimize loss functions, balancing error pull and overfitting push.
result Evolved loss functions effectively reduce overfitting, leading to better performance and robustness.
The Zone of Avoidance makes it difficult for astronomers to catalogue galaxies at low latitudes to our galactic plane due to high star densities and extinction. However, having a complete sky map of galaxies is important in a number of fields of research in astronomy. There are many unclassified sources of light in the…
Paper improves deep learning for solving evolutionary equations with trainable hard constraints.
problem Low computational accuracy of standard PINNs in large temporal domains.
method Sequential learning strategies and trainable influence functions for hard constraints.
result Significantly improved computational accuracy and universality of the method.
Many biological characteristics of evolutionary interest are not scalar variables but continuous functions. Here we use phylogenetic Gaussian process regression to model the evolution of simulated function-valued traits. Given function-valued data only from the tips of an evolutionary tree and utilising independent pri…
We are often interested in clustering objects that evolve over time and identifying solutions to the clustering problem for every time step. Evolutionary clustering provides insight into cluster evolution and temporal changes in cluster memberships while enabling performance superior to that achieved by independently c…
this paper has been withdrawn
A neural network and evolutionary algorithm framework designs nonlinear optical molecules.
problem Designing efficient nonlinear optical materials.
method Multi-stage Bayesian neural network (msBNN) and corrected Lewis-mode group contribution method (cLGC) combined with evolutionary algorithm (EA).
result Accurately and efficiently designs molecules with different optical properties using a small data set.
BoGA combines evolutionary search with Bayesian optimization for efficient protein design.
problem Designing novel proteins with specific characteristics is challenging due to sequence space complexity.
method BoGA integrates a genetic algorithm with Bayesian optimization to efficiently explore sequence space.
result BoGA accelerates discovery of high-confidence binders for diverse protein design objectives.
The paper improves evolutionary computation by optimizing selection rates.
problem Choosing the right selection rate in evolutionary computation.
method The paper proves mathematically that a selection rate of μ/λ leads to better progress rates and provides a theoretical basis for this.
result The theoretical selection rate μ/λ leads to a better progress rate of order O(λ^-1) compared to O(λ^-2/d).
Cryptocurrencies evolve through survival of the fittest, modeled with evolutionary finance.
problem Understanding the dynamics of cryptocurrency markets.
method Evolutionary finance concepts applied to toy models of cryptocurrency data.
result Survival of the fittest in cryptofinance is explained through scaling laws.
The key idea of this model is that firms are the result of an evolutionary process. Based on demand and supply considerations the evolutionary model presented here derives explicitly Gibrat's law of proportionate effects as the result of the competition between products. Applying a preferential attachment mechanism for…
BEKAN uses RBFs and evolutionary methods to solve PDEs with boundary conditions.
problem Enforcing boundary conditions in neural networks for PDE solutions.
method Boundary condition-guaranteed evolutionary Kolmogorov-Arnold Network (BEKAN) with radial basis functions (RBFs). Incorporates Dirichlet, periodic, and Neumann conditions.
result BEKAN outperforms MLP and B-splines KAN in solving PDEs with boundary conditions.
Proves FR-NGD optimally approximates evolutionary dynamics and continuous Bayesian inference.
problem Optimizing continuous time replicator equations and continuous Bayesian inference.
method Fisher-Rao natural gradient descent (FR-NGD) and its correspondence with evolutionary dynamics.
result FR-NGD optimally approximates continuous time replicator equations and continuous Bayesian inference.
EPNE models evolving network patterns for better predictions.
problem Capturing evolving patterns in dynamic networks.
method EPNE models temporal network evolution using causal convolutions and a temporal objective function.
result EPNE outperforms other methods in various prediction tasks.
DyHATR learns dynamic heterogeneous networks for better link prediction.
problem Learning effective representations of dynamic heterogeneous networks for link prediction.
method Hierarchical attention for heterogeneous information and temporal RNN for evolutionary patterns.
result DyHATR significantly outperforms state-of-the-art baselines on link prediction tasks.