5 papers
Multiplicative learning from observation-prediction ratios
Han Kim, Hyungjoon Soh, Vipul Periwal +1
Additive parameter updates, as used in gradient descent and its adaptive extensions, underpin most modern machine-learning optimization. Yet, such additive schemes often demand num…
Variational Garrote for Sparse Inverse Problems
Kanghun Lee, Hyungjoon Soh, Junghyo Jo
Sparse regularization plays a central role in solving inverse problems arising from incomplete or corrupted measurements. Different regularizers correspond to different prior assum…
Stochastic Clock Attention for Aligning Continuous and Ordered Sequences
Hyungjoon Soh, Junghyo Jo
We formulate an attention mechanism for continuous and ordered sequences that explicitly functions as an alignment model, which serves as the core of many sequence-to-sequence task…
Variational Garrote for Statistical Physics-based Sparse and Robust Variable Selection
Hyungjoon Soh, Dongha Lee, Vipul Periwal +1
Selecting key variables from high-dimensional data is increasingly important in the era of big data. Sparse regression serves as a powerful tool for this purpose by promoting model…
Unified Cross-modal Translation of Score Images, Symbolic Music, and Performance Audio
Jongmin Jung, Dongmin Kim, Sihun Lee +5
Music exists in various modalities, such as score images, symbolic scores, MIDI, and audio. Translations between each modality are established as core tasks of music information re…