The paper interprets policy-gradient algorithms using continuation theory.
problem Optimizing nonconvex functions in reinforcement learning.
method Formulates policy optimization as optimization by continuation, interprets policy-gradient algorithms as implicitly optimizing deterministic policies.
result Exploration in policy-gradient algorithms is seen as computing a continuation of the return of the policy.
Proposes a continuous relaxation for discrete Bayesian optimization.
problem Efficiently optimizing discrete data with limited target observations.
method Continuous relaxation of objective function, incorporating prior knowledge.
result Optimization can be computationally tractable with few observations.
Bayesian optimization tackles mixed discrete-continuous problems with Gaussian processes.
problem Optimizing problems with both discrete and continuous variables using costly simulations.
method Relaxing discrete variables into continuous latent variables, using Bayesian optimization, and incorporating compatibility constraints with Lagrangians.
result Comparative analysis of different mixed Bayesian optimization approaches.
The paper studies continuous submodular functions and their optimization.
problem Maximizing continuous submodular functions in poly. time.
method Characterization of continuous submodularity, operations preserving it, and algorithms for constrained maximization.
result Continuous submodularity is equivalent to a weak DR property, leading to continuous DR-submodular functions with the full DR property.
New research suggests continual learning should focus on both optimization objective and optimization trajectory.
problem Even with perfect joint loss approximation, continual learning still suffers from forgetting when starting a new task.
method Proposes focusing on both optimization objective and optimization trajectory, combining replay-approximated joint objectives with gradient projection-based optimization routines.
result Combining replay-approximated joint objectives with gradient projection-based optimization routines did not show clear benefits in initial experiments.
New algorithm optimizes Hölder continuous functions efficiently.
problem Optimizing Hölder continuous multivariate functions.
method Uses a query creation rule for global optimization, avoiding proxy functions.
result Achieves an average regret bound of $O(T^{- racα{n}})$ for Hölder exponent α. Investment strategy optimization from discrete to continuous models.
problem Optimizing investment strategies and stopping times in both continuous and discrete settings.
method Characterized value functions via quadratic reflected BSDEs for continuous case, discretized BSDEs for discrete case, and derived uniform convergence rates.
result Uniform convergence and rate from discrete to continuous quadratic reflected BSDEs.
iMOCA optimizes multiple objectives with continuous approximations for resource efficiency.
problem Optimizing multiple objectives with continuous function approximations that balance accuracy and evaluation cost.
method Information-Theoretic Multi-Objective Bayesian Optimization with Continuous Approximations (iMOCA) selects input and function approximations to maximize information gain per unit cost.
result iMOCA significantly improves over existing single-fidelity methods in approximating the optimal Pareto set.
Novel proof shows continuity of optimal transport feasible set mapping.
problem Continuity of feasible set mapping in optimal transport problems.
method Presented a novel and shorter proof of continuity.
result Established continuity of the feasible set mapping.
Study optimal stopping problems with finite-time horizon and proves continuity and strict monotonicity of the boundary.
problem Optimal stopping problems with finite-time horizon and state-dependent discounting.
method Linear diffusion process, time-homogeneous gain function, fine regularity properties, continuity and strict monotonicity proof.
result Proves continuity and strict monotonicity of the optimal stopping boundary under mild assumptions.
This paper tackles convex-submodular minimax problems in mixed continuous-discrete domains.
problem Convex-submodular minimax problems in mixed continuous-discrete domains.
method Introduces new notions of optimality and proposes iterative algorithms combining discrete and continuous optimization.
result Characterizes convergence rates, computational complexity, and quality of solutions for convex and monotone-submodular minimax problems.
Paper introduces a continuous convexity measure for compact sets.
problem Lack of continuity in existing convexity measures.
method Enriched axioms with continuity hypothesis in Hausdorff's sense.
result Theoretical grounding and continuous convexity measure construction.
A new method for hierarchical clustering using continuous embeddings and optimization.
problem Hierarchical clustering with provable quality guarantees.
method Continuous relaxation of discrete optimization problem using hyperbolic embeddings and decoding.
result Continuous relaxation yields a discrete tree with (1 + epsilon)-factor approximation for optimal tree.
We present the first PAC optimal algorithm for Bayes-Adaptive Markov Decision Processes (BAMDPs) in continuous state and action spaces, to the best of our knowledge. The BAMDP framework elegantly addresses model uncertainty by incorporating Bayesian belief updates into long-term expected return. However, computing an e…
Many scientific questions require estimating the effects of continuous treatments. Outcome modeling and weighted regression based on the generalized propensity score are the most commonly used methods to evaluate continuous effects. However, these techniques may be sensitive to model misspecification, extreme weights o…
New method solves continuous time mean-variance model for consistent investment strategy.
problem Time-consistent optimal strategy for continuous time mean-variance model.
method Developed a new Bellman principle method.
result Obtained a time-consistent dynamic optimal strategy.
Optimal task order improves continual learning performance.
problem Challenges in neural networks learning multiple tasks in sequence.
method Linear teacher-student model with latent factors, derived analytical expression.
result Two principles for optimal task order: least representative first and dissimilar adjacent tasks.
Though neural networks have achieved much progress in various applications, it is still highly challenging for them to learn from a continuous stream of tasks without forgetting. Continual learning, a new learning paradigm, aims to solve this issue. In this work, we propose a new model for continual learning, called Ba…
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.
New method uses continuous OT for fairness, outperforming discrete OT.
problem Fairness issues in machine learning models.
method Stochastic-gradient fairness method based on continuous optimal transport.
result Continuous OT method outperforms discrete OT when data is limited.
New approach shows continuity and compactness of martingale measures.
problem Stability of martingale optimal transport problem.
method Set-valued map theory and lower-upper hemicontinuity.
result Lower and upper hemicontinuity of the set of martingale measures.
Consider power utility maximization of terminal wealth in a 1-dimensional continuous-time exponential Levy model with finite time horizon. We discretize the model by restricting portfolio adjustments to an equidistant discrete time grid. Under minimal assumptions we prove convergence of the optimal discrete-time strate…
New method optimizes decision-making in uncertain environments.
problem Optimal decision-making under partial observability.
method Nested sequential Monte Carlo algorithm for continuous POMDPs.
result Demonstrated effectiveness on continuous POMDP benchmarks.
We aim to construct the optimal solutions to the undiscounted continuous-time infinite horizon optimization problems, the objective functionals of which may be unbounded. We identify the condition under which the limit of the solutions to the finite horizon problems is optimal for the infinite horizon problems under th…
Continuous-time algorithms improve online learning performance.
problem Online learning with sequential data and minimizing overall regret.
method Extending discrete-time algorithms to continuous-time models for online linear optimization, adversarial bandit, and adversarial linear bandit.
result Optimal regret bounds are proven for continuous-time settings.
Paper solves POMDPs in continuous time and discrete spaces.
problem Optimal decision making in discrete state and action space systems under partial observability.
method Combining optimal filtering theory and deep learning to solve a Hamilton-Jacobi-Bellman equation.
result Derives a mathematical description and solution approach for continuous-time POMDPs.
Efficient deep policy gradient method for continuous-time control problems.
problem Optimal control in continuous time with fine time discretization.
method Multi-scale deep policy gradient method with varying time discretization.
result Targeted efficiency in computational resources achieved through multi-scale approach.
Value-based reinforcement learning (RL) methods like Q-learning have shown success in a variety of domains. One challenge in applying Q-learning to continuous-action RL problems, however, is the continuous action maximization (max-Q) required for optimal Bellman backup. In this work, we develop CAQL, a (class of) algor…
Ada-BKB optimizes black-box functions on continuous domains with adaptive discretization.
problem Optimizing functions with continuous domains using Gaussian process optimization.
method Adaptive discretization of the function domain to avoid non-convex optimization costs.
result Ada-BKB algorithm runs in O(T2dexteff2), significantly faster than existing methods. The paper proves optimal smoothness for certain Lagrangian graphs with specific Hölder continuity.
problem Optimal regularity for Hölder continuous Hamiltonian stationary Lagrangian graphs.
method Establishing smoothness conditions based on Hölder exponent and Lagrangian phase properties.
result Smoothness of graphs is achieved when Hölder exponent is strictly greater than 1/3 and Lagrangian phase is supercritical.
Paper proves EM algorithm convergence for mixtures of discrete and continuous parameters.
problem Nontrivial convergence analysis for EM algorithms with mixed-integer parameters.
method Introduces conditions for EM convergence in mixed-integer optimization.
result Proves convergence of EM-based sparse Bayesian learning algorithm.
CRA improves UL-based CO solvers by dynamically smoothing and enforcing discreteness.
problem Local optima and artificial rounding issues in UL-based CO solvers.
method Continuous Relaxation Annealing (CRA) strategy that dynamically shifts from continuous to discrete solutions.
result Significantly enhances UL-based CO solver performance and eliminates artificial rounding.
Hybrid Policy Optimization tackles reinforcement learning in hybrid spaces, improving performance over PPO.
problem Credit assignment issues and biased gradients in hybrid discrete-continuous action spaces.
method Mixed gradient estimator combining pathwise and score-function gradients, reformulating problems in hybrid form.
result HPO substantially outperforms PPO on inventory control and switched systems, with performance gaps increasing with continuous action dimension.
Paper studies continuous prediction with experts' advice using differential equations.
problem Continuous prediction with experts' advice in online learning.
method Continuous-time stochastic calculus and differential equations.
result Improved guarantees for quantile regret with continuous-time algorithm.
Bilevel Continual Learning improves continual learning by transferring knowledge effectively.
problem Catastrophic forgetting and poor generalization in continual learning.
method Bilevel optimization and dual memory management strategies.
result BCL achieves effective knowledge transfer and alleviates catastrophic forgetting.
A graph VAE framework optimizes neural architectures in a continuous space.
problem Discovering efficient neural architectures in a discrete space.
method Graph VAE framework with VAE and GNN components, joint learning of predictors and decoders.
result The framework discovers powerful neural architectures with both excellent performance and high computational efficiency.
New approach to continual learning prioritizes adaptation over retention.
problem Catastrophic forgetting in lifelong learning models.
method Formalized CL as an online optimization problem, introduced Transfer Efficiency, and derived a Critical Task Duration.
result Retention can hinder real-time adaptation in non-stationary environments.
Study on optimal portfolio selection with varying borrowing and saving rates in continuous-time markets.
problem Optimal portfolio selection in markets with different borrowing and saving rates.
method Hamilton-Jacobi-Bellman equation, partial differential equation, verification argument.
result Existence and smoothness of the value function, identification of trading regions and strategies.
Simulated annealing is a popular method for approaching the solution of a global optimization problem. Existing results on its performance apply to discrete combinatorial optimization where the optimization variables can assume only a finite set of possible values. We introduce a new general formulation of simulated an…
Counterexamples to continuity of optimal transportation on Riemannian manifolds with everywhere positive sectional curvature are provided. These examples show that the condition A3w of Ma, Trudinger, & Wang is not guaranteed by positivity of sectional curvature.
New method generates continuous Pareto sets for multi-task learning.
problem Challenges in finding optimal solutions for correlated multi-task learning problems.
method Efficiently generates locally continuous Pareto sets and fronts in multi-objective optimization problems.
result Demonstrates continuous analysis of Pareto optimal solutions in machine learning problems.
Avanzi et al. (2016) recently studied an optimal dividend problem where dividends are paid both periodically and continuously with different transaction costs. In the Brownian model with Poissonian periodic dividend payment opportunities, they showed that the optimal strategy is either of the pure-continuous, pure-peri…
New algorithm improves causal effect estimation for continuous treatments.
problem Observational causal inference with continuous treatments.
method End-to-end entropy balancing for maximizing causal inference accuracy.
result Our algorithm estimates causal effect more accurately than baseline.
We study the problem of policy evaluation and learning from batched contextual bandit data when treatments are continuous, going beyond previous work on discrete treatments. Previous work for discrete treatment/action spaces focuses on inverse probability weighting (IPW) and doubly robust (DR) methods that use a reject…
Many real-world functions are defined over both categorical and category-specific continuous variables and thus cannot be optimized by traditional Bayesian optimization (BO) methods. To optimize such functions, we propose a new method that formulates the problem as a multi-armed bandit problem, wherein each category co…
New method uses dynamic programming for meta continual learning.
problem Challenges of generalization and catastrophic forgetting in sequential learning.
method Developed a theoretical framework using dynamic programming for meta continual learning.
result Theoretical and practical method achieves better accuracy than existing methods.
The paper analyzes continuous optimization for DAG structure learning and its limitations.
problem The performance of continuous structure learning approaches is not consistent after data standardization.
method Analysis of continuous optimization for DAG structure learning, focusing on equal and non-equal noise variances.
result Continuous structure learning approaches may not perform well after data standardization, especially with non-equal noise variances.
Study a continuous portfolio optimization with a new CVaR-like constraint using martingale approach.
problem Optimizing a portfolio under a new CVaR-like constraint that is not compatible with traditional methods.
method Follows a martingale approach in a complete market setting, solving a convex constrained minimization problem.
result Obtains a tractable and interpretable characterization of the optimal strategy.