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.
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.
We discuss multi-task online learning when a decision maker has to deal simultaneously with M tasks. The tasks are related, which is modeled by imposing that the M-tuple of actions taken by the decision maker needs to satisfy certain constraints. We give natural examples of such restrictions and then discuss a general …
We explore machine learning methods for AC Optimal Powerflow (ACOPF) - the task of optimizing power generation in a transmission network according while respecting physical and engineering constraints. We present two formulations of ACOPF as a machine learning problem: 1) an end-to-end prediction task where we directly…
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.
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.
Novel framework for Bayesian neural networks incorporating task-specific constraints.
problem Task-specific constraints in supervised model deployment.
method Introduces Output-Constrained BNN (OC-BNN) framework.
result OC-BNNs effectively incorporate prior expert knowledge and desiderata like safety and fairness.
A multi-task GP model tracks time-varying transition probabilities between two states.
problem Tracking time-varying transition probabilities between 'moves' and 'pauses' states.
method Kernel-based multi-task Gaussian Process model with time-variability and constraints.
result Enforces constraints while learning transition probabilities.
New neural network smoothness constraints improve model performance.
problem Improving model sensitivity to input changes for better generalization and robustness.
method Exploring current smoothness constraints and proposing new flexible definitions.
result Current smoothness constraints lack flexibility and understanding of data, tasks, and learning.
POLICE enforces linear constraints on deep neural networks efficiently.
problem Enforcing constraints on deep neural networks without affecting optimization.
method Provably optimal affine constraint enforcement method that minimally modifies DNNs.
result POLICE ensures DNNs fulfill affine constraints during training and testing.
Study identifies specialist representations from generalist models without parametric constraints.
problem Identify task-relevant latent representations from generalist models.
method Nonparametric, fully unsupervised approach, proving identifiability of task structure and latent representations.
result Identifiability of task structure and latent representations in a nonparametric setting.
In standard reinforcement learning (RL), a learning agent seeks to optimize the overall reward. However, many key aspects of a desired behavior are more naturally expressed as constraints. For instance, the designer may want to limit the use of unsafe actions, increase the diversity of trajectories to enable exploratio…
Pattern sampling has been proposed as a potential solution to the infamous pattern explosion. Instead of enumerating all patterns that satisfy the constraints, individual patterns are sampled proportional to a given quality measure. Several sampling algorithms have been proposed, but each of them has its limitations wh…
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…
New method optimizes experiments under constraints.
problem Adapting BED to dynamic constraints in real-world tasks.
method Offline pre-training of an amortized policy and posterior network with online multi-step lookahead planning.
result Significantly more informative design sequences than existing methods.
Study compares adaptive vs fixed query learning methods.
problem Comparing adaptive and fixed query learning methods for task approximation.
method Examined in-context and agentic learning in two settings: unrestricted and realizable.
result Adaptivity does not hinder performance in unrestricted setting but can in realizable setting.
A new method combines SciML and UQ with physical constraints.
problem Uncertainty quantification in scientific machine learning tasks.
method Physics-constrained polynomial chaos expansion.
result Effective uncertainty quantification and SciML integration.
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.
We propose a method to impose homogeneous linear inequality constraints of the form Ax≤0 on neural network activations. The proposed method allows a data-driven training approach to be combined with modeling prior knowledge about the task. One way to achieve this task is by means of a projection step at test time…
A new ML method teaches constraints directly to models.
problem Addressing safety and fairness in AI systems.
method Directly teaching constraint satisfaction to ML models using a constraint solver.
result Empirically, our approach performs well on fairness and synthetic constraints.
Unified analysis of multi-task functional linear regression with manifold and composite penalties.
problem Estimating slope functions from functional data with multi-task learning.
method Penalized splines with manifold constraint and composite quadratic penalty.
result Unified convergence upper bound and phase transition behaviors for estimators.
New method avoids failures in physics-constrained systems using active learning.
problem Handling fatal failures in systems governed by physics constraints.
method Develops a novel active learning method that considers implicit physics constraints.
result Achieves zero-failure in composite fuselage assembly process without explicit failure regions.
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.
Bayesian algorithms improve crowdsourcing with label and instance constraints.
problem Efficiently labeling large datasets with additional human annotator information.
method Developed Bayesian algorithms for semi-supervised crowdsourced classification under label and instance constraints.
result Improved performance compared to unsupervised crowdsourcing on various datasets.
Solving tasks in Reinforcement Learning is no easy feat. As the goal of the agent is to maximize the accumulated reward, it often learns to exploit loopholes and misspecifications in the reward signal resulting in unwanted behavior. While constraints may solve this issue, there is no closed form solution for general co…
SOFARI improves inference on multi-task learning latent factors.
problem Challenges in precise inference on multi-task learning latent factor matrices.
method High-dimensional manifold-based Neyman near-orthogonality inference on Stiefel manifold structure.
result Easy-to-use bias-corrected estimators for latent factor vectors and singular values with asymptotic normal distributions.
Reinforcement learning (RL) for robotics is challenging due to the difficulty in hand-engineering a dense cost function, which can lead to unintended behavior, and dynamical uncertainty, which makes exploration and constraint satisfaction challenging. We address these issues with a new model-based reinforcement learnin…
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.
New diffusion models handle constrained domains, improving generative tasks.
problem Diffusion models struggle with manifolds defined by inequality constraints.
method Developed two noising processes: logarithmic barrier metric and reflected Brownian motion.
result Demonstrated practical utility on synthetic and real-world 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.
SpodNet learns SPD matrices with structural constraints.
problem Estimating SPD matrices with additional structural constraints.
method Introduces SpodNet, a neural network module that guarantees SPD outputs and supports structural constraints.
result SpodNet learns SPD and sparse matrices effectively.
A framework estimates categorical distributions under constraints, ensuring generality and uniqueness.
problem Estimating categorical distributions summarizing sample data under marginal constraints.
method Theoretical framework + Iterative Proportional Fitting (IPF) to estimate the distribution.
result A unique categorical distribution of Maximum Entropy under marginal constraints exists and is estimated.
Study financial market graphs with Laplacian constraints.
problem Learning undirected graphs in financial markets.
method Proposes algorithms to estimate graphs accounting for financial data properties.
result Guidelines for estimating graphs in financial markets.
In this paper, we proposed a general framework for data poisoning attacks to graph-based semi-supervised learning (G-SSL). In this framework, we first unify different tasks, goals, and constraints into a single formula for data poisoning attack in G-SSL, then we propose two specialized algorithms to efficiently solve t…
Study on policy testing in MDPs with lower bounds and new algorithm.
problem Deciding if policy value exceeds a threshold with limited samples.
method Derived lower bound, proposed new algorithm, reformulated problem, used policy optimization in reversed MDP.
result New algorithm outperforms existing methods in policy testing.
New method robustly discovers causal relationships from imperfect data.
problem Challenges in causal discovery from imperfect structural constraints.
method Prior alignment and conflict resolution through surrogate model and multi-task learning.
result Proposes a robust method for causal discovery under imperfect constraints.
We develop a highly scalable optimization method called "hierarchical group-thresholding" for solving a multi-task regression model with complex structured sparsity constraints on both input and output spaces. Despite the recent emergence of several efficient optimization algorithms for tackling complex sparsity-induci…
Dynamic submodular maximization with consistency constraints.
problem Maximizing submodular functions in a streaming environment with limited changes.
method Algorithms with trade-offs between consistency and approximation quality.
result Effective algorithms for real-world applications.
Unified framework for integrating linear constraints in time series forecasting.
problem Challenges in traditional time series forecasting algorithms.
method Unified framework combining linear constraints in time series forecasting.
result Exact minimizer of the constrained empirical risk can be computed efficiently using linear algebra.
This paper proposes Relational Similarity Machines (RSM): a fast, accurate, and flexible relational learning framework for supervised and semi-supervised learning tasks. Despite the importance of relational learning, most existing methods are hard to adapt to different settings, due to issues with efficiency, scalabili…
Deep learning for supervised learning has achieved astonishing performance in various machine learning applications. However, annotated data is expensive and rare. In practice, only a small portion of data samples are annotated. Pseudo-ensembling-based approaches have achieved state-of-the-art results in computer visio…
Enhanced neural network framework improves constraint satisfaction with topological conditioning.
problem Maintaining semantic coherence while satisfying physical and logical constraints in neuro-symbolic reasoning.
method Integrates topological conditioning with gradient stabilization mechanisms using Forman-Ricci curvature, Deep Delta Learning, and Covariance Matrix Adaptation Evolution Strategy.
result Achieves mean energy reduction to 1.15 compared to baseline values of 11.68, with 95 percent success rate.
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.
Proposes a framework for compositional generalization in language models.
problem Lack of compositional generalization in neural networks compared to humans.
method Introduces Generalized Grammar Rules (GGRs) for transduction tasks, formalizing symmetry-based constraints.
result Framework enables models to generalize compositionally, similar to human learning.
Recurrent Neural Networks (RNNS) are now widely used on sequence generation tasks due to their ability to learn long-range dependencies and to generate sequences of arbitrary length. However, their left-to-right generation procedure only allows a limited control from a potential user which makes them unsuitable for int…
Automates model selection for GLMs using optimization.
problem Automating model selection for generalized linear models.
method Mixed-integer conic optimization for feature subset selection and model constraints.
result Optimization of AIC and BIC criteria with multicollinearity constraints.
We showed how to use trained neural networks to perform Bayesian reasoning in order to solve tasks outside their initial scope. Deep generative models provide prior knowledge, and classification/regression networks impose constraints. The tasks at hand were formulated as Bayesian inference problems, which we approximat…
Optimizes train schedules and maintenance using CP and QA.
problem Optimizing train schedules and maintenance considering constraints.
method Used Constraint Programming and Quantum Annealing to model and solve the problem.
result Both CP and QA approaches produce comparable results on real quantum computers.