Optimistic algorithm reduces regret and constraint violations in online convex optimization with adversarial constraints.
problem Online convex optimization with adversarial constraints.
method Improved algorithm using accurate predictions of loss and constraint functions.
result Improved bounds on regret and cumulative constraint violations.
Paper tackles constrained bandit problems with a new learning framework.
problem Optimizing a black-box reward function subject to a black-box constraint function over a continuous space.
method Rectified Pessimistic-Optimistic Learning (RPOL) framework, incorporating optimistic and pessimistic GP bandit learning.
result RPOL achieves sublinear regret and minimal cumulative constraint violation.
LinConTS improves regret and constraint violations in probabilistic linearly constrained bandits.
problem Maximizing cumulative reward under probabilistic linear constraints.
method LinConTS, a Thompson Sampling-based algorithm for bandits with linear constraints.
result LinConTS achieves O(log T) regret and constraint violations for suboptimal arms.
New algorithm reduces constraint violation to O ( T 1 / 3 ) O(T^{1/3}) O ( T 1/3 ) while maintaining O ( T ) O(\sqrt{T}) O ( T ) regret.
problem Minimizing static regret and cumulative constraint violation in constrained online convex optimization.
method Proposes an algorithm that achieves O ( T ) O(\sqrt{T}) O ( T ) regret and O ( T 1 / 3 ) O(T^{1/3}) O ( T 1/3 ) cumulative constraint violation. result Shows that O ( T 1 / 3 ) O(T^{1/3}) O ( T 1/3 ) cumulative constraint violation is achievable with O ( T ) O(\sqrt{T}) O ( T ) regret. We present an adaptive online gradient descent algorithm to solve online convex optimization problems with long-term constraints , which are constraints that need to be satisfied when accumulated over a finite number of rounds T , but can be violated in intermediate rounds. For some user-defined trade-off parameter β β β …
New algorithm reduces regret and constraint violation in online convex optimization with complex constraints.
problem Online convex optimization with multiple functional constraints and a simple constraint set.
method Instance-dependent bound using online primal-dual mirror-prox algorithm in general normed spaces.
result Achieves an O(√V*(T)) regret and O(1) constraint violation, improving over previous works.
New approach tackles resource constraints in bandit problems with weakly adaptive algorithms.
problem Maximizing rewards while adhering to general long-term constraints.
method Weakly adaptive primal and dual regret minimizers.
result Achieves sublinear constraints violations and competitive ratios in both stochastic and adversarial settings.
Optimal bounds on regret and constraint violation in adversarial COCO.
problem Minimizing regret and cumulative constraint violation in adversarial COCO.
method New surrogate loss function and Follow-the-Regularized-Leader/Online Gradient Descent.
result Achieved optimal O ( T ) O(\sqrt{T}) O ( T ) bounds on both regret and cumulative constraint violation. Paper tackles online DR-submodular maximization with stochastic constraints.
problem Maximizing utility while adhering to a cumulative resource constraint in an online setting.
method Proposes OLFW algorithm to solve the problem of online continuous DR-submodular maximization with linear stochastic constraints.
result Obtains sub-linear regret and constraint violation bounds.
In this work we consider adversarial contextual bandits with risk constraints. At each round, nature prepares a context, a cost for each arm, and additionally a risk for each arm. The learner leverages the context to pull an arm and then receives the corresponding cost and risk associated with the pulled arm. In additi…
New algorithms for constrained online optimization with memory and predictions.
problem Control of constrained dynamical systems and scheduling with reconfiguration budgets.
method Proposed algorithms achieving sublinear regret and constraint violation under time-varying constraints, both with and without predictions.
result First algorithms achieving sublinear regret and constraint violation in constrained online optimization with memory.
Decentralized algorithm for online optimization with long-term constraints.
problem Distributed online optimization with long-term constraints over time-varying graphs.
method Proposed decentralized algorithm with regret and constraint violation bounds.
result Regret and constraint violation upper bounds achieved for various loss functions and feedback types.
New RL algorithm achieves sublinear regret and constraint violation without simulators.
problem Maximizing reward under utility constraints in large-scale systems.
method Model-free, simulator-free algorithm using LSVI-UCB with primal-dual optimization and soft-max policy.
result Achieves i l d e O ( d 3 H 3 T ) ilde{\mathcal{O}}(\sqrt{d^3H^3T}) i l d e O ( d 3 H 3 T ) regret and i l d e O ( d 3 H 3 T ) ilde{\mathcal{O}}(\sqrt{d^3H^3T}) i l d e O ( d 3 H 3 T ) constraint violation bounds. FISAR uses neural networks to optimize safe reinforcement learning with forward-invariant constraints.
problem Safe reinforcement learning with constraints in safety-critical environments.
method Imposing linear constraints on policy parameters' updating dynamics, using a DNN-based optimizer to satisfy these constraints.
result The policy decreases constraint violation and maximizes cumulative reward monotonically.
Paper improves COCO problem, reducing constraint violation at the cost of slightly more regret.
problem Online Convex Optimization with adversarial constraints.
method Proposes new policies that trade off regret for reduced constraint violation.
result Achieves i l d e O ( d T + T β ) ilde{O}(\sqrt{dT}+ T^β) i l d e O ( d T + T β ) regret and i l d e O ( d T 1 − β ) ilde{O}(dT^{1-β}) i l d e O ( d T 1 − β ) CCV. Improved COCO algorithms with better constraint control.
problem Achieving small regret and constraint violation in online convex optimization.
method Simple projection-based algorithm leveraging self-contraction geometry.
result Exponential improvement in cumulative constraint violation for strongly convex losses.
Optimizes resource allocation in a network with random job requests.
problem Minimizing costs while satisfying job requests within a budget.
method Formalizes as a repeated game, proposes an online saddle-point algorithm.
result Upper bounds for regret and constraint violations are derived.
New algorithm optimizes online network resource allocation with long-term constraints.
problem Optimal resource reservation in communication networks with job transfers and budget limits.
method Randomized exponentially weighted method for long-term constraints.
result Upper bound for regret and cumulative constraint violations established.
SEEDA optimizes dose allocation in clinical trials to balance efficacy and safety.
problem Complex relationships between efficacy and toxicity in new drug trials.
method Adaptive clinical trial methodology that maximizes cumulative efficacy while ensuring safety constraints.
result SEEDA outperforms existing methods in finding optimal doses with higher success rates and fewer patients.
This paper considers online convex optimization over a complicated constraint set, which typically consists of multiple functional constraints and a set constraint. The conventional online projection algorithm (Zinkevich, 2003) can be difficult to implement due to the potentially high computation complexity of the proj…
A new RL method handles uncertainty and constraints in real-time optimization.
problem Real-time optimization under process uncertainty and constraints.
method Chance-constrained reinforcement learning to handle probabilistic state constraints.
result Satisfies process constraints with high probability in real-time.
Algorithm minimizes loss and constraint violations in online convex optimization with smooth penalties.
problem Minimizing loss and constraint violations in online convex optimization with smooth penalties.
method Projected gradient descent over a set around the current action.
result Both dynamic regret and constraint violation are bounded by the path-length.
IPO optimizes reinforcement learning with constraints for better performance.
problem Maximizing long-term reward while satisfying cumulative constraints in decision problems.
method Interior-point Policy Optimization (IPO) using logarithmic barrier functions.
result IPO outperforms state-of-the-art baselines in reward maximization and constraint satisfaction.
Algorithm ensures privacy while strictly adhering to constraints.
problem Differential privacy with linear constraints that must be strictly followed.
method Developed an algorithm that releases a nearly-optimal solution satisfying constraints with probability 1.
result Achieved nearly optimal performance while preserving privacy and strictly adhering to constraints.
Meta-gradient D4PG optimizes performance and constraint adherence in RL.
problem Balancing performance and adherence to complex constraints in RL.
method Uses meta-gradients to find a balance between expected return and minimizing constraint violations.
result Meta-gradient D4PG consistently outperforms baselines across MuJoCo domains.
Paper tackles robust MDPs with sample complexity guarantees.
problem Learning safe policies in uncertain environments.
method Introduces augmented state space and RCVI algorithm.
result First sample complexity guarantee for RCMDPs.
Wireless communication systems operate in complex time-varying environments. Therefore, selecting the optimal configuration parameters in these systems is a challenging problem. For wireless links, \emph{rate selection} is used to select the optimal data transmission rate that maximizes the link throughput subject to a…
Some high-dimensional data.sets can be modelled by assuming that there are many different linear constraints, each of which is Frequently Approximately Satisfied (FAS) by the data. The probability of a data vector under the model is then proportional to the product of the probabilities of its constraint violations. We …
New algorithms control loss and constraints in uncertain, changing environments.
problem Adapting to adversarial constraints in uncertain, changing environments.
method Developed algorithms for constrained MAB problems with optimal rates of regret and positive constraint violation.
result Achieved optimal rates of regret and positive constraint violation under varying degrees of adversariality.
In many real-world reinforcement learning (RL) problems, besides optimizing the main objective function, an agent must concurrently avoid violating a number of constraints. In particular, besides optimizing performance it is crucial to guarantee the safety of an agent during training as well as deployment (e.g. a robot…
This paper considers distributed online optimization with time-varying coupled inequality constraints. The global objective function is composed of local convex cost and regularization functions and the coupled constraint function is the sum of local convex functions. A distributed online primal-dual dynamic mirror des…
This work compares regularization and constrained inference for label constraints in machine learning.
problem Improving model performance with label constraints in machine learning.
method Comparison of regularization and constrained inference strategies.
result Constrained inference reduces population risk by correcting model violations, while regularization narrows the generalization gap but introduces bias.
New algorithm reduces regret and constraint violation in online convex optimization with predictions.
problem Online convex optimization with time-varying constraints and predictions.
method Primal-dual algorithm combining Follow-The-Regularized-Leader with adaptive steps.
result Achieves O ( T 3 − β 4 ) \mathcal O(T^{\frac{3-β}{4}}) O ( T 4 3 − β ) regret and O ( T 1 + β 2 ) \mathcal O(T^{\frac{1+β}{2}}) O ( T 2 1 + β ) constraint violation bounds. Novel method for efficient optimization of noisy, expensive hybrid models.
problem Efficient optimization of hybrid models with noisy observations and constraints.
method Constrained Upper Quantile Bound (CUQB) method exploiting composite structure.
result Significantly improved sampling efficiency and theoretical guarantees.
New algorithm solves constrained MDPs with generative model, reducing sample complexity.
problem Maximizing rewards while adhering to constraints in MDPs.
method Primal-dual framework using mirror descent value iteration.
result Near-optimal sample complexity bounds for CMDPs.
New methods reduce constraint violations to certainty in stochastic optimization.
problem Finding a point with certain constraint satisfaction and near-stationarity.
method Single-loop variance-reduced stochastic first-order methods with truncated momentum schemes.
result Achieves strong convergence guarantees for ε ε ε -stochastic stationary points with certain constraint satisfaction. Canary optimizes VaR-constrained RL problems with a conservative bound using Cantelli's inequality.
problem Optimizing reinforcement learning policies under VaR constraints in dense cost regimes.
method Employing Cantelli's inequality to create a conservative and smooth bound on VaR constraints based on moments of cost returns. Extending trust-region framework for worst-case bounds on policy improvement and constraint violation.
result Canary reliably satisfies VaR constraints with fewest violations and earliest permanent satisfaction, while maintaining reward competitiveness.
The paper calculates bounds for risk metrics and entropies under partial information constraints.
problem Analyzing risk metrics and entropies for unimodal, symmetric distributions with limited information.
method Develops lower and upper bounds for worst-case distortion riskmetrics and weighted entropy for unimodal, symmetric distributions with known mean and variance.
result Sharp upper bounds for distortion riskmetrics and weighted entropy for symmetric distributions.
New framework for resilient bi-criteria optimization under noisy feedback.
problem Bi-criteria combinatorial optimization with noisy function evaluations.
method Introducing ( α , β , δ , e x t t t N ) (α,β,δ, exttt{N}) ( α , β , δ , e x ttt N ) -resilience and developing a black-box framework. result Achieves sublinear regret and constraint violation for bi-criteria bandit problems.
Safe linear bandits over unknown polytopes avoid safety violations and suboptimal actions.
problem Online approach to linear programming with unknown constraints and risks.
method Doubly-optimistic strategy (DOSS) for safe linear bandits over polytopes.
result DOSS achieves tight bounds on efficacy regret and safety violations.
Chance-constrained ActInf allows for small violations of constraints to drive goal-directed behavior.
problem Goal-directed behavior constrained by prior beliefs.
method Introducing chance constraints to ActInf, allowing for small violations of constraints.
result Chance-constrained ActInf allows for a trade-off between robust control and chance constraint violation.
NucleusDiff models atomic nuclei interactions to prevent separation violations in drug design.
problem Maintaining minimum pairwise distance between atoms to avoid separation violations in drug design.
method Enforces distance constraint between atomic nuclei and manifolds in a diffusion model.
result Reduces separation violations by up to 100.00% and enhances binding affinity by up to 22.16%.
New algorithm reduces regret in CMDPs without cancellation of errors.
problem Lagrangian approaches in CMDPs struggle with cancellation of errors.
method OptAug-CMDP, based on augmented Lagrangian method.
result Regret of i l d e O ( K ) ilde{O}(\sqrt{K}) i l d e O ( K ) for both objective and constraint violation. This paper considers online convex optimization (OCO) with stochastic constraints, which generalizes Zinkevich's OCO over a known simple fixed set by introducing multiple stochastic functional constraints that are i.i.d. generated at each round and are disclosed to the decision maker only after the decision is made. Th…
Study optimizes portfolio allocation policies using off-policy data and constraints.
problem Optimizing portfolio allocation policies under constraints using off-policy data.
method Solves a minimax objective with off-policy estimators and online learning to control constraint violations.
result Constructs near-optimal allocation policies for various regimes of operation and constraints.
The paper analyzes CMDPs, balancing exploration and exploitation to avoid constraint violations.
problem Balancing exploration and exploitation in CMDPs to satisfy constraints.
method Two approaches: optimistic planning and incremental updates of primal and dual variables.
result Both approaches achieve sublinear regret on utility and constraint violations, with stronger guarantees for the linear programming approach.
Improved online learning with time-varying constraints for complex domains.
problem Constrained online convex optimization with time-varying constraints.
method Constructing a composite surrogate loss and using the online Frank-Wolfe method.
result Novel regret and cumulative constraint violation bounds for strongly convex losses.
New algorithm reduces sample complexity for safe reinforcement learning.
problem Safe reinforcement learning in constrained MDPs with performance and safety constraints.
method Model-based primal-dual algorithm balancing regret and bounded constraint violations.
result Proves near-optimal policies with bounded violations or zero violations in CMDPs.