arXiv research

New findings show second-order scoring rules can't accurately represent epistemic uncertainty.

Loss minimisation fails to capture epistemic uncertainty in second-order predictors.

New algorithm TURTLE outperforms MAML and meta-learner LSTM.

Second-order optimizers retain residual information after data deletion, affecting machine unlearning.

New algorithm learns HMM parameters on Riemannian manifolds.

Biological evolution has distilled the experiences of many learners into the general learning algorithms of humans. Our novel meta reinforcement learning algorithm MetaGenRL is inspired by this process. MetaGenRL distills the experiences of many complex agents to meta-learn a low-complexity neural objective function th…

Online learning with limited information feedback (bandit) tries to solve the problem where an online learner receives partial feedback information from the environment in the course of learning. Under this setting, Flaxman et al.[8] extended Zinkevich's classical Online Gradient Descent (OGD) algorithm [29] by proposi…

A boosting method improves nonparametric density estimation without smoothing assumptions.

New damping technique improves deep learning models by reducing noise in flat directions.

Improved regret bounds for adversarial linear contextual bandits.

New budget quantifies drift in closed-loop learning, improving reproducibility.

The paper introduces new measures for quantifying uncertainty in machine learning.

Optimal algorithm converts weak to strong learner with less data.

Inverse reinforcement learning (IRL) enables an agent to learn complex behavior by observing demonstrations from a (near-)optimal policy. The typical assumption is that the learner's goal is to match the teacher's demonstrated behavior. In this paper, we consider the setting where the learner has its own preferences th…

Meta clustering categorizes learners for collaborative learning.

New meta-learners estimate time-varying treatment effects without model assumptions.

New algorithm improves convergence of gradient boosting trees.

Boosting algorithms are frequently used in applied data science and in research. To date, the distinction between boosting with either gradient descent or second-order Newton updates is often not made in both applied and methodological research, and it is thus implicitly assumed that the difference is irrelevant. The g…

New survival learners estimate heterogeneous treatment effects from time-to-event data.

Proposes a method to integrate learner models robustly against misspecifications.

VTIRT speeds up IRT inference for dynamic learner proficiency.

Method selects the best deep learner for time-series prediction using Bayesian networks.

One of the most ambitious use cases of computer-assisted learning is to build a recommendation system for lifelong learning. Most recommender algorithms exploit similarities between content and users, overseeing the necessity to leverage sensible learning trajectories for the learner. Lifelong learning thus presents un…

In this paper, we make an important step towards the black-box machine teaching by considering the cross-space machine teaching, where the teacher and the learner use different feature representations and the teacher can not fully observe the learner's model. In such scenario, we study how the teacher is still able to …

pystacked combines machine learning models for improved predictions.

MTL2L learns to adapt optimisation rules for unseen data.

Teaches sequential learners with changing inner states to improve future performance.

Theorem ensures superior learning outcomes for authorized learners with quantum label encoding.

Second-order economic theory considers new variables to improve price volatility predictions.

Meta-learners improve causal effect estimation in small samples.

The paper presents a method for personalized exercise recommendations that improves learner skill gain.

sGBM speeds up gradient boosting by parallelizing and adapting base learners.

Deep reinforcement learning algorithms have been successfully applied to a range of challenging control tasks. However, these methods typically struggle with achieving effective exploration and are extremely sensitive to the choice of hyperparameters. One reason is that most approaches use a noisy version of their oper…

New LT-O-learners improve HLTE estimation with low overlap.

Paper introduces GDR-learners for estimating potential outcomes from observational data.

Exact second-order optimization for deep learning reduces computational cost and improves performance.

An algorithm learns from multiple models to match an oracle's risk.

SOLBP extends efficient inference to uncertain Bayesian networks.

LARP filters data to protect model performance across various learners.

Developed a theory of local convexity for second order differential equations on Lie algebroids.

In this paper, we consider the problem of machine teaching, the inverse problem of machine learning. Different from traditional machine teaching which views the learners as batch algorithms, we study a new paradigm where the learner uses an iterative algorithm and a teacher can feed examples sequentially and intelligen…

Machine teaching addresses the problem of finding the best training data that can guide a learning algorithm to a target model with minimal effort. In conventional settings, a teacher provides data that are consistent with the true data distribution. However, for sequential learners which actively choose their queries,…

Improved off-policy selection and learning in contextual bandits with better guarantees.

Data-driven model selection reduces regret in sequential decisions.

Study evaluates different meta-learners for multi-view stacking.

Paper examines risk measure expansions under FGM dependence, improving accuracy at extreme levels.

Negative step sizes improve second-order methods for neural networks.

This paper analyzes meta-learners for estimating multi-valued treatment effects.