arXiv research

New framework improves generative models with prediction and consistency constraints.

New algorithm reduces regret and constraint violation in online convex optimization with predictions.

Recently there has been sustained interest in modifying prediction algorithms to satisfy fairness constraints. These constraints are typically complex nonlinear functionals of the observed data distribution. Focusing on the path-specific causal constraints proposed by Nabi and Shpitser (2018), we introduce new theoreti…

Optimistic algorithm reduces regret and constraint violations in online convex optimization with adversarial constraints.

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…

New algorithms for constrained online optimization with memory and predictions.

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…

New loss function handles uncertain constraints in CSLO problems.

Bayesian Entropy Neural Networks enforce constraints on deep learning predictions.

The paper improves Gaussian processes by adding sum constraints, enhancing prediction accuracy.

A smart method predicts and optimizes decisions online with resource constraints.

Proposes a recursive MPC scheme with probabilistic safety guarantees for uncertain dynamic systems.

DiffSlack learns neural networks with nonlinear constraints via learnable slack variables.

The paper tackles MAP inference over non-convex constraints in safety-critical settings.

Paper presents a framework to automatically discover constraints from data.

Proposes a Gaussian process model for constrained dynamics learning.

Constraint-based learning reduces the burden of collecting labels by having users specify general properties of structured outputs, such as constraints imposed by physical laws. We propose a novel framework for simultaneously learning these constraints and using them for supervision, bypassing the difficulty of using d…

PhysVarMix predicts diverse urban trajectories with physics constraints.

We suggest ways to enforce given constraints in the output of a Generative Adversarial Network (GAN) generator both for interpolation and extrapolation (prediction). For the case of dynamical systems, given a time series, we wish to train GAN generators that can be used to predict trajectories starting from a given ini…

Two methods are proposed for high-dimensional shape-constrained regression and classification. These methods reshape pre-trained prediction rules to satisfy shape constraints like monotonicity and convexity. The first method can be applied to any pre-trained prediction rule, while the second method deals specifically w…

This work is a further study on the Generalized Constraint Neural Network (GCNN) model [1], [2]. Two challenges are encountered in the study, that is, to embed any type of prior information and to select its imposing schemes. The work focuses on the second challenge and studies a new constraint imposing scheme for equa…

A new framework for information theory considers computational constraints.

Unknown constraints arise in many types of expensive black-box optimization problems. Several methods have been proposed recently for performing Bayesian optimization with constraints, based on the expected improvement (EI) heuristic. However, EI can lead to pathologies when used with constraints. For example, in the c…

Algorithm minimizes regret while adhering to unknown safety constraints.

Bayesian search optimizes exploration of feasible solutions under expensive constraints.

Develops a new method for optimizing with uncertain data.

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…

The paper tackles fair set-valued classification under demographic parity constraints.

New framework improves reliability of learned representations by modeling uncertainty and structural constraints.

Parallel BO method for multi-objective optimization with constraints.

Bayesian model predicts crack evolution on rails with uncertainties.

In this paper, we propose an end-to-end deep learning model, called E2Efold, for RNA secondary structure prediction which can effectively take into account the inherent constraints in the problem. The key idea of E2Efold is to directly predict the RNA base-pairing matrix, and use an unrolled algorithm for constrained p…

The paper relaxes constraints on predictive coding models, making them more biologically plausible.

We study online prediction where regret of the algorithm is measured against a benchmark defined via evolving constraints. This framework captures online prediction on graphs, as well as other prediction problems with combinatorial structure. A key aspect here is that finding the optimal benchmark predictor (even in hi…

Model predicts stable molecules with AI and physics constraints.

This work presents PESMOC, Predictive Entropy Search for Multi-objective Bayesian Optimization with Constraints, an information-based strategy for the simultaneous optimization of multiple expensive-to-evaluate black-box functions under the presence of several constraints. PESMOC can hence be used to solve a wide range…

The goal of ordinal embedding is to represent items as points in a low-dimensional Euclidean space given a set of constraints in the form of distance comparisons like "item $i$ is closer to item $j$ than item $k$". Ordinal constraints like this often come from human judgments. To account for errors and variation in jud…

New method uses predictions to infer causal effects without labeled data.

ParamBoost uses gradient boosting to create interpretable non-linear models with constraints.

The paper proposes DEA to make graph neural networks fairer in link prediction.

Domain knowledge helps detect adversarial examples in multi-label classification.

We propose a method to model multi-agent behaviors with limited observation and mechanical constraints.

Proposes a non-crossing deep neural network quantile regression method.

This paper benchmarks monotone-constrained models for credit PD across datasets and finds constraints are mostly costless.

Proposes a framework for partially fair machine learning models.

Performance analysis, from the external point of view of a client who would only have access to returns and holdings of a fund, evolved towards exact attribution made in the context of portfolio optimisation, which is the internal point of view of a manager controlling all the parameters of this optimisation. Attributi…

Recent work in learning ontologies (hierarchical and partially-ordered structures) has leveraged the intrinsic geometry of spaces of learned representations to make predictions that automatically obey complex structural constraints. We explore two extensions of one such model, the order-embedding model for hierarchical…

We demonstrate a new deep learning autoencoder network, trained by a nonnegativity constraint algorithm (NCAE), that learns features which show part-based representation of data. The learning algorithm is based on constraining negative weights. The performance of the algorithm is assessed based on decomposing data into…