arXiv research

Adversarial MoE learns category-specific models for product search.

Paper improves COCO problem, reducing constraint violation at the cost of slightly more regret.

Bayesian method estimates dynamics from near-optimal trajectories.

Algorithm identifies intended fairness constraints from expert demonstrations for fair clustering.

This study analyzes communication constraints in MoE architectures using information theory.

HS-MoE selects sparse experts using adaptive priors and data-adaptive gating.

Combines expert models using Kullback-Leibler divergence to create a combined model.

New approach to sparse optimal transport for matching tokens with experts.

Develops a functional mix-of-experts model for multiclass classification.

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…

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

This work improves Gaussian process inference using mixtures of experts and nested SMC samplers.

Framework allows systems to defer difficult decisions to unknown experts.

Study improves privacy-preserving online prediction from experts with speed-ups.

While most approaches to the problem of Inverse Reinforcement Learning (IRL) focus on estimating a reward function that best explains an expert agent's policy or demonstrated behavior on a control task, it is often the case that such behavior is more succinctly represented by a simple reward combined with a set of hard…

New algorithms improve online prediction from experts with privacy constraints.

Investigates fast prediction rates with limited expert advice.

The paper proposes a semi-parametric Bayesian network model using Gaussian Processes and Horseshoe priors.

The goal of meta-learning is to train a model on a variety of learning tasks, such that it can adapt to new problems within only a few iterations. Here we propose a principled information-theoretic model that optimally partitions the underlying problem space such that specialized expert decision-makers solve the result…

L2D-CD learns to defer expert recommendations in causal discovery.

Combines neural networks and expert rules for concept-based learning.

MLDemon monitors ML systems post-deployment, improving reliability with real-time performance estimates and expert labels.

In this paper, we study Reinforcement Learning from Demonstrations (RLfD) that improves the exploration efficiency of Reinforcement Learning (RL) by providing expert demonstrations. Most of existing RLfD methods require demonstrations to be perfect and sufficient, which yet is unrealistic to meet in practice. To work o…

The paper proposes a method to explain expert decisions by modeling preferences with 'what if' outcomes.

New algorithms improve prediction with expert advice under local differential privacy.

Specialized hierarchies improve decision-making by partitioning tasks.

Algorithm learns expert weights to minimize regret in adversarial setting.

The paper shows regularization can't always find all optimal solutions in constrained ML.

Model explains capital allocation and wealth distribution dynamics in a frictional economy.

Optimizes quantile and semi-adversarial regret with novel root-logarithmic regularizers.

A Human-in-the-Loop Bayesian Optimization framework for constraint-aware bioprocess development.

Novel framework for Bayesian neural networks incorporating task-specific constraints.

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…

Active researches are currently being performed to incorporate the wealth of scientific knowledge into data-driven approaches (e.g., neural networks) in order to improve the latter's effectiveness. In this study, the Theory-guided Neural Network (TgNN) is proposed for deep learning of subsurface flow. In the TgNN, as s…

Crowdsourced training of large neural networks with decentralized Mixture-of-Experts.

Combinatorial optimization problems are typically tackled by the branch-and-bound paradigm. We propose a new graph convolutional neural network model for learning branch-and-bound variable selection policies, which leverages the natural variable-constraint bipartite graph representation of mixed-integer linear programs…

Active learning agents typically employ a query selection algorithm which solely considers the agent's learning objectives. However, this may be insufficient in more realistic human domains. This work uses imitation learning to enable an agent in a constrained environment to concurrently reason about both its internal …

Framework learns robust control policies from expert demonstrations.

New algorithms approximate Rashomon set for sparse models, aiding expert interaction.

SkyGP improves Gaussian process scalability for real-time learning.

Resource scheduling and coordination is an NP-hard optimization requiring an efficient allocation of agents to a set of tasks with upper- and lower bound temporal and resource constraints. Due to the large-scale and dynamic nature of resource coordination in hospitals and factories, human domain experts manually plan a…

Model accurately gates ocean microbes from high-frequency flow cytometry data.

Entropy based ideas find wide-ranging applications in finance for calibrating models of portfolio risk as well as options pricing. The abstracted problem, extensively studied in the literature, corresponds to finding a probability measure that minimizes relative entropy with respect to a specified measure while satisfy…

Multi-expert L2D underfits more severely, requiring new methods.

TENP prunes experts and neurons in Mixture-of-Experts models for efficient deployment.

PARAFAC2 has demonstrated success in modeling irregular tensors, where the tensor dimensions vary across one of the modes. An example scenario is modeling treatments across a set of patients with the varying number of medical encounters over time. Despite recent improvements on unconstrained PARAFAC2, its model factors…

A method to select important experts for Gaussian processes to balance computational efficiency and uncertainty quantification.

Extends Demographic Parity for fairer wage predictions with expert knowledge.