80 citations · 243 across the 11 of their papers we have counts for
6 papers · 1 filter
TSPulse: Tiny Pre-Trained Models with Disentangled Representations for Rapid Time-Series Analysis
Vijay Ekambaram, Subodh Kumar, Arindam Jati +5
Time-series tasks often benefit from signals expressed across multiple representation spaces (e.g., time vs. frequency) and at varying abstraction levels (e.g., local patterns vs.…
Predictive Optimization with Zero-Shot Domain Adaptation
Tomoya Sakai, Naoto Ohsaka
Prediction in a new domain without any training sample, called zero-shot domain adaptation (ZSDA), is an important task in domain adaptation. While prediction in a new domain has g…
Do We Need Zero Training Loss After Achieving Zero Training Error?
Takashi Ishida, Ikko Yamane, Tomoya Sakai +2
Overparameterized deep networks have the capacity to memorize training data with zero \emph{training error}. Even after memorization, the \emph{training loss} continues to approach…
Convex Formulation of Multiple Instance Learning from Positive and Unlabeled Bags
Han Bao, Tomoya Sakai, Issei Sato +1
Multiple instance learning (MIL) is a variation of traditional supervised learning problems where data (referred to as bags) are composed of sub-elements (referred to as instances)…
Semi-Supervised Classification Based on Classification from Positive and Unlabeled Data
Tomoya Sakai, Marthinus Christoffel du Plessis, Gang Niu +1
Most of the semi-supervised classification methods developed so far use unlabeled data for regularization purposes under particular distributional assumptions such as the cluster a…
Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning
Gang Niu, Marthinus Christoffel du Plessis, Tomoya Sakai +2
In PU learning, a binary classifier is trained from positive (P) and unlabeled (U) data without negative (N) data. Although N data is missing, it sometimes outperforms PN learning…