Adaptive hedging under delayed feedback

Korotin, Alexander; V’yugin, Vladimir V.; Burnaev, Evgeny

doi:10.1016/j.neucom.2019.06.106

Cited by 8 publications

(6 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, a variety of works highlight sample complexity and topological properties [103], [104] of these distances. We further highlight that ICNNs are gaining an increasing attention by the ML community, especially in generative modeling [161], [162]. Furthermore, ICNNs represent a good case of ML for OT.…”

Section: Conclusion and Future Directions 81 Computational Optimal Tr...mentioning

confidence: 87%

Cross-domain fault diagnosis through optimal transport for a CSTR process

et al. 2022

View full text Add to dashboard Cite

Section: Conclusion and Future Directions 81 Computational Optimal Tr...mentioning

confidence: 87%

Cross-domain fault diagnosis through optimal transport for a CSTR process

et al. 2022

View full text Add to dashboard Cite

“…; F is the cumulative distribution function (CDF) associated with the underlying distribution. 1-Wasserstein distance satisfies positivedefiniteness, symmetry, and triangle inequality (Nietert et al 2022;Korotin, Selikhanovych, and Burnaev 2023;Chen et al 2023c,b;Naderializadeh et al 2021). Problem Definition.…”

Section: Preliminaries and Problem Formulationmentioning

confidence: 99%

Deep Structural Knowledge Exploitation and Synergy for Estimating Node Importance Value on Heterogeneous Information Networks

Chen,

Fang,

Wang

et al. 2024

AAAI

View full text Add to dashboard Cite

The classic problem of node importance estimation has been conventionally studied with homogeneous network topology analysis. To deal with practical network heterogeneity, a few recent methods employ graph neural models to automatically learn diverse sources of information. However, the major concern revolves around that their fully adaptive learning process may lead to insufficient information exploration, thereby formulating the problem as the isolated node value prediction with underperformance and less interpretability. In this work, we propose a novel learning framework namely SKES. Different from previous automatic learning designs, SKES exploits heterogeneous structural knowledge to enrich the informativeness of node representations. Then based on a sufficiently uninformative reference, SKES estimates the importance value for any input node, by quantifying its informativeness disparity against the reference. This establishes an interpretable node importance computation paradigm. Furthermore, SKES dives deep into the understanding that "nodes with similar characteristics are prone to have similar importance values" whilst guaranteeing that such informativeness disparity between any different nodes is orderly reflected by the embedding distance of their associated latent features. Extensive experiments on three widely-evaluated benchmarks demonstrate the performance superiority of SKES over several recent competing methods.

show abstract

“…Among lots of existing learner's strategies for combining experts predictions [2,4,3], the Vovk's aggregating algorithm [8] (AA for short) is typically considered to be the best. For a wide class of loss functions λ (called η-mixable for some constant η > 0) it provides the way to efficiently combine experts predictions {γ n t } N n=1 to a single γ t so that learner achieves small regret bound.…”

Section: T Domentioning

confidence: 99%

Integral Mixability: a Tool for Efficient Online Aggregation of Functional and Probabilistic Forecasts

Korotin¹,

V’yugin²,

Burnaev³

2019

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper we extend the setting of the online prediction with expert advice to function-valued forecasts. At each step of the online game several experts predict a function and the learner has to efficiently aggregate these functional forecasts into one a single forecast. We adapt basic mixable loss functions to compare functional predictions and prove that these "integral" expansions are also mixable. We call this phenomena integral mixability. As an application, we consider various loss functions for prediction of probability distributions and show that they are mixable by using our main result. The considered loss functions include Continuous ranking probability score (CRPS), Optimal transport costs (OT), Beta-2 and Kullback-Leibler (KL) divergences.1 Merge, mix, average, etc.

show abstract

Adaptive hedging under delayed feedback

Cited by 8 publications

References 27 publications

Cross-domain fault diagnosis through optimal transport for a CSTR process

Cross-domain fault diagnosis through optimal transport for a CSTR process

Deep Structural Knowledge Exploitation and Synergy for Estimating Node Importance Value on Heterogeneous Information Networks

Integral Mixability: a Tool for Efficient Online Aggregation of Functional and Probabilistic Forecasts

Contact Info

Product

Resources

About