61 citations · 123 across the 8 of their papers we have counts for
8 papers
Utilizing Reinforcement Learning for de novo Drug Design
Hampus Gummesson Svensson, Christian Tyrchan, Ola Engkvist +1
Deep learning-based approaches for generating novel drug molecules with specific properties have gained a lot of interest in the last few years. Recent studies have demonstrated pr…
Shift of Pairwise Similarities for Data Clustering
Morteza Haghir Chehreghani
Several clustering methods (e.g., Normalized Cut and Ratio Cut) divide the Min Cut cost function by a cluster dependent factor (e.g., the size or the degree of the clusters), in or…
A Deep Learning Framework for Generation and Analysis of Driving Scenario Trajectories
Andreas Demetriou, Henrik Alfsvåg, Sadegh Rahrovani +1
We propose a unified deep learning framework for the generation and analysis of driving scenario trajectories, and validate its effectiveness in a principled way. To model and gene…
Efficient Optimization of Dominant Set Clustering with Frank-Wolfe Algorithms
Carl Johnell, Morteza Haghir Chehreghani
We study Frank-Wolfe algorithms - standard, pairwise, and away-steps - for efficient optimization of Dominant Set Clustering. We present a unified and computationally efficient fra…
Analysis of Knowledge Transfer in Kernel Regime
Arman Rahbar, Ashkan Panahi, Chiranjib Bhattacharyya +2
Knowledge transfer is shown to be a very successful technique for training neural classifiers: together with the ground truth data, it uses the "privileged information" (PI) obtain…
Do Kernel and Neural Embeddings Help in Training and Generalization?
Arman Rahbar, Emilio Jorge, Devdatt Dubhashi +1
Recent results on optimization and generalization properties of neural networks showed that in a simple two-layer network, the alignment of the labels to the eigenvectors of the co…
Unsupervised Representation Learning with Minimax Distance Measures
Morteza Haghir Chehreghani
We investigate the use of Minimax distances to extract in a nonparametric way the features that capture the unknown underlying patterns and structures in the data. We develop a gen…
Learning Representations from Dendrograms
Morteza Haghir Chehreghani, Mostafa Haghir Chehreghani
We propose unsupervised representation learning and feature extraction from dendrograms. The commonly used Minimax distance measures correspond to building a dendrogram with single…