Hierarchical Lattice Layer for Partially Monotone Neural Networks
Nov 28, 2022
Speakers
Hiroki Yanagisawa
Speaker · 0 followers
Kohei Miyaguchi
Speaker · 0 followers
Takayuki Katsuki
Speaker · 0 followers
About
Partially monotone regression is a regression analysis in which the target values are monotonically increasing with respect to a subset of input features. The TensorFlow Lattice library is one of the standard machine learning libraries for partially monotone regression. It consists of several neural network layers, and its core component is the lattice layer. One of the problems of the lattice layer is its requirement for a special training algorithm to satisfy monotonicity constraints. Another problem is that it cannot receive a high-dimensional input vector due to the resultant memory consumption. We propose a novel neural network layer, the hierarchical lattice layer (HLL), as an extension of the lattice layer so that we can use a standard neural network algorithm to train HLL while satisfying monotonicity constraints and so that it can receive a high-dimensional input vector. Our experiments demonstrate that HLL did not sacrifice its prediction performance on real datasets compared with the lattice layer.Partially monotone regression is a regression analysis in which the target values are monotonically increasing with respect to a subset of input features. The TensorFlow Lattice library is one of the standard machine learning libraries for partially monotone regression. It consists of several neural network layers, and its core component is the lattice layer. One of the problems of the lattice layer is its requirement for a special training algorithm to satisfy monotonicity constraints. Another…
Organizer
NeurIPS 2022
Account · 957 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
MorphTE: Injecting Morphology in Tensorized Embeddings
Watch later
Guobing Gan, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
De Novo Protein Design
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Toward Efficient Robust Training against Union of ℓ_p Threat Models
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Closing Remarks
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Structured Q-learning For Antibody Design
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%