CoCoRL learns safe constraints from demonstrations with unknown rewards.
problem Learning safe constraints from demonstrations with different unknown rewards.
method Convex Constraint Learning for Reinforcement Learning (CoCoRL) constructs a convex safe set based on demonstrations.
result CoCoRL learns constraints that lead to safe driving behavior and can safely transfer to different tasks and environments.
Develops a new method for optimizing with uncertain data.
problem Uncertainty in real-world optimization problems.
method Combines chance constraints and constraint learning for mixed-integer linear optimization.
result Data-driven solution for setting probabilistic bounds on learned constraints.
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.
Iterative method learns unknown constraints for MPC control.
problem Learning to satisfy unknown polyhedral state constraints in iterative MPC.
method Collects and improves estimates of unknown constraints using collected data, designs an MPC controller to satisfy the estimated constraints.
result Robust and probabilistic guarantees of constraint satisfaction as a function of task iterations.
We present an objective function for learning with unlabeled data that utilizes auxiliary expectation constraints. We optimize this objective function using a procedure that alternates between information and moment projections. Our method provides an alternate interpretation of the posterior regularization framework (…
Proposes a method to learn both constraints and objective functions from data.
problem Data-driven inverse optimization for mixed-integer linear programs (MILPs).
method Two-stage approach: first learns constraints, then estimates objective-function weights conditioned on learned constraints.
result Proposes and validates a method for learning both objective functions and constraints from data.
New algorithm clusters data and learns kernels without relaxing constraints.
problem Learning kernels or distance metrics from pairwise constraints without losing generalization.
method Joint clustering and kernel learning without relaxing constraints.
result Outperforms existing approaches on diverse datasets.
Algorithm minimizes regret while adhering to unknown safety constraints.
problem Online learning with unknown safety constraints.
method General meta-algorithm leveraging online regression and learning oracles.
result Concrete algorithm with T \sqrt{T} T regret for linear constraints. 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.
ACOL learns constraints from human preferences in driving simulations.
problem Learning constraints from human preferences in driving simulations.
method Adaptive Constraint Learning (ACOL) algorithm for constrained linear best-arm identification.
result ACOL's sample complexity matches worst-case lower bound and is significantly tighter in the average case.
This work proposes an online learning approach to tighten constraints in stochastic control problems.
problem Solving chance-constrained stochastic optimal control problems is computationally challenging.
method Reformulate chance constraints as a binary regression problem and use a GP model to learn constraint-tightening parameters online.
result The approach tightens constraints more effectively, leading to lower costs in numerical experiments.
DC3 uses deep learning to solve hard-constrained optimization problems efficiently.
problem Hard constraints in optimization problems make classical solvers slow and infeasible.
method DC3 employs a differentiable procedure to enforce feasibility and unrolls corrections for inequality constraints.
result DC3 achieves near-optimal solutions while maintaining feasibility in both synthetic and real-world tasks.
Algorithm tackles constrained reinforcement learning with concave-convex and knapsack constraints.
problem Constrained episodic reinforcement learning with concave rewards and convex constraints.
method Modular analysis with strong theoretical guarantees for concave-convex and knapsack settings.
result Significantly outperforms existing approaches in constrained episodic environments.
We reformulate data-dependent constraints to ensure they are always met with high probability.
problem Ensuring fairness and stability in machine learning models with data-dependent constraints.
method Calibrated reformulation of constraints to guarantee satisfaction with a specified probability.
result Our method guarantees that fairness constraints are met at test time with high probability.
Proposes Constrained Q-learning for reinforcement learning with constraints.
problem Optimizing multiple objectives while adhering to constraints in reinforcement learning.
method Directly restricts the action space in Q-update to learn optimal Q-function for constrained MDP.
result Improves safety and optimality in high-level decision making for autonomous driving.
Survey of Gaussian process constraints for modeling expensive data.
problem Modeling expensive data with physical constraints.
method Overview of various Gaussian process constraints and their implementation.
result Discussion of computational challenges introduced by constraints.
Algorithm safely learns from sub-optimal baseline policies while satisfying constraints.
problem Safe reinforcement learning with constraints when baseline policy is sub-optimal.
method Iterative policy optimization alternating between return maximization, baseline distance minimization, and constraint projection.
result Consistently outperforms baselines, achieving 10x fewer constraint violations and 40% higher reward.
In order to satisfy safety conditions, an agent may be constrained from acting freely. A safe controller can be designed a priori if an environment is well understood, but not when learning is employed. In particular, reinforcement learned (RL) controllers require exploration, which can be hazardous in safety critical …
The paper improves Gaussian processes by adding sum constraints, enhancing prediction accuracy.
problem Improving Gaussian process predictions with background knowledge constraints.
method Conditioning the prior distribution on sum constraints to ensure fulfillment of linear and nonlinear constraints.
result The approach fulfills constraints with high precision and improves prediction accuracy.
Study Federated RL with diverse constraints, proposing new optimization methods.
problem Solving reinforcement learning with multiple constraints in federated learning.
method Federated primal-dual policy optimization methods based on policy gradient methods.
result FedNPG achieves global convergence with an i l d e O ( 1 / T ) ilde{O}(1/\sqrt{T}) i l d e O ( 1/ T ) rate. Many machine learning approaches are characterized by information constraints on how they interact with the training data. These include memory and sequential access constraints (e.g. fast first-order methods to solve stochastic optimization problems); communication constraints (e.g. distributed learning); partial acce…
New algorithms reduce orthogonality constraint enforcement time in machine learning.
problem Efficiently solving orthogonality constraints in machine learning.
method Extending the landing algorithm to Stiefel manifold, incorporating stochastic and variance reduction techniques.
result All proposed methods achieve the same convergence rate as Riemannian counterparts enforcing constraints.
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.
Proposes a Gaussian process model for constrained dynamics learning.
problem Challenges in identifying constrained dynamics of mechanical systems.
method Combines analytical mechanics with Gaussian process regression.
result Improves data efficiency and constraint integrity in predictions.
Paper presents a framework to automatically discover constraints from data.
problem Discovering constraints from data for structured output prediction.
method Formulates structured output prediction as ILP, mines constraints by estimating polytopes of feasible set.
result Successfully identifies feasible sets and constraints for various tasks.
New framework improves generative models with prediction and consistency constraints.
problem Improving generative models with sparse labeled data.
method Optimizes variational autoencoders with prediction and consistency constraints.
result Promising image classification performance, especially in semi-supervised scenarios.
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.
Study uses DRL with Lagrangian relaxation to solve temporal control tasks with STL constraints.
problem Optimal control problems with temporal logic constraints.
method Extended CMDP formulation, Lagrangian relaxation, two-phase constrained DRL algorithm.
result Demonstrated learning performance of the proposed algorithm through simulations.
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.
This paper explores the potential of Lagrangian duality for learning applications that feature complex constraints. Such constraints arise in many science and engineering domains, where the task amounts to learning optimization problems which must be solved repeatedly and include hard physical and operational constrain…
Adding constraint support in Machine Learning has the potential to address outstanding issues in data-driven AI systems, such as safety and fairness. Existing approaches typically apply constrained optimization techniques to ML training, enforce constraint satisfaction by adjusting the model design, or use constraints …
Consistent algorithms for multiclass learning with complex metrics and constraints.
problem Learning with complex performance metrics and constraints.
method General framework for designing consistent algorithms by viewing the problem as an optimization over feasible confusion matrices.
result Rates of convergence to the optimal (feasible) classifier, showing asymptotic consistency.
When learning policies for real-world domains, two important questions arise: (i) how to efficiently use pre-collected off-policy, non-optimal behavior data; and (ii) how to mediate among different competing objectives and constraints. We thus study the problem of batch policy learning under multiple constraints, and o…
DePAint solves MARL for agents with local constraints, privacy, and no central controller.
problem Training multi-agent systems to optimize rewards while adhering to safety constraints in a decentralized setting.
method Formulated as a decentralized constrained multi-agent Markov Decision Problem, proposed DePAint method using momentum-based decentralized policy gradient.
result First privacy-preserving fully decentralized MARL algorithm considering both peak and average constraints.
We consider the problem of metric learning subject to a set of constraints on relative-distance comparisons between the data items. Such constraints are meant to reflect side-information that is not expressed directly in the feature vectors of the data items. The relative-distance constraints used in this work are part…
DiffSlack learns neural networks with nonlinear constraints via learnable slack variables.
problem Enforcing nonlinear inequality constraints in neural networks.
method DiffSlack reformulates inequalities as equalities with learnable slack variables, predicting them as part of the network output.
result DiffSlack achieves higher planning success rates and stronger geometric constraint satisfaction compared to existing methods.
New method for private learning with fairness constraints.
problem Rate-constrained optimization under differential privacy.
method RaCO-DP, a DP variant of SGDA solving Lagrangian formulation.
result Empirical results show RaCO-DP outperforms existing methods.
We assume that we are given a time series of data from a dynamical system and our task is to learn the flow map of the dynamical system. We present a collection of results on how to enforce constraints coming from the dynamical system in order to accelerate the training of deep neural networks to represent the flow map…
Study optimal policies under budget and coverage constraints.
problem Optimal policy learning with budget and coverage constraints.
method Combination of knapsack structure, affine threshold rule, linear programming relaxation, Greedy-Lagrangian (GLC), and rank-and-cut (RC) algorithms.
result GLC closely approximates the optimal solution and achieves near-optimal performance in finite samples; RC is approximately optimal under certain conditions.
Most learning methods with rank or sparsity constraints use convex relaxations, which lead to optimization with the nuclear norm or the ℓ 1 \ell_1 ℓ 1 -norm. However, several important learning applications cannot benefit from this approach as they feature these convex norms as constraints in addition to the non-convex rank a…
Paper proposes a model-free algorithm for CMDPs with long-term constraints, achieving optimal regret bounds.
problem Optimizing systems with long-term constraints where transition probabilities are unknown.
method Combines concepts from constrained optimization and Q-learning to propose an algorithm.
result Achieves optimal regret bounds for reward and constraint violation.
New DAG constraints improve differentiable DAG learning.
problem Recovering DAG structures from observational data is hard due to combinatorial optimization.
method Developed analytic functions to formulate DAG constraints, closed under differentiation, summation, and multiplication.
result Analytic DAG constraints outperform previous methods in various settings.
Paper studies sparsity and DAG constraints for learning linear DAGs.
problem Learning DAGs from data is challenging due to the large search space.
method Formulates structure learning as a constrained optimization problem with soft sparsity and DAG constraints.
result Soft sparsity and DAG constraints lead to an easier optimization problem.
Stabilized neural differential equations enforce constraints on dynamical systems.
problem Ensuring dynamical systems preserve known constraints like conservation laws.
method SNDEs with a stabilization term to enforce manifold constraints.
result SNDEs outperform existing methods and broaden constraint types.
HardNet adds hard constraints to neural networks without sacrificing performance.
problem Ensuring adherence to input-dependent constraints in neural networks.
method Appends a differentiable enforcement layer to neural networks for end-to-end training with hard constraint guarantees.
result HardNet retains neural networks' universal approximation capabilities and enables efficient optimization.
The paper introduces an adjacency constraint to improve goal-conditioned HRL.
problem Training inefficiency in goal-conditioned HRL due to large action space.
method Restricting the high-level action space to a k-step adjacent region of the current state.
result The adjacency constraint preserves optimal hierarchical policies and improves HRL performance.
Active learning improves SR by proposing experiments in data-limited settings.
problem Efficiently gathering data for symbolic regression with physical constraints.
method Query by committee using the Pareto frontier of equations, with physical constraints.
result Reduces data required for SR and achieves state-of-the-art results.
Incorporating constraints is a major concern in probabilistic machine learning. A wide variety of problems require predictions to be integrated with reasoning about constraints, from modelling routes on maps to approving loan predictions. In the former, we may require the prediction model to respect the presence of phy…