Patients who undergo mechanical heart valve replacements or have conditions like Atrial Fibrillation have to take Vitamin K Antagonists (VKA) drugs to prevent coagulation of blood. These drugs have narrow therapeutic range and need to be very closely monitored due to life threatening side effects. The dosage of VKA drug is determined and revised by a physician based on Prothrombin Time - International Normalised Ratio (PT-INR) value obtained through a blood test. Our work aimed at predicting the maintenance dosage of warfarin, the present most widely recommended anticoagulant drug, using the de-identified medical data collected from 109 patients from Kerala. A Support Vector Machine (SVM) Regression model was built to predict the maintenance dosage of warfarin, for patients who have been undergoing treatment from a physician and have reached stable INR values between 2.0 and 4.0.

We develop a method for computing policies in Markov decision processes with risk-sensitive measures subject to temporal logic constraints. Specifically, we use a particular risk-sensitive measure from cumulative prospect theory, which has been previously adopted in psychology and economics. The nonlinear transformation of the probabilities and utility functions yields a nonlinear programming problem, which makes computation of optimal policies typically challenging. We show that this nonlinear weighting function can be accurately approximated by the difference of two convex functions. This observation enables efficient policy computation using convex-concave programming. We demonstrate the effectiveness of the approach on several scenarios.

Tree data occurs in many forms, such as computer programs, chemical molecules, or natural language. Unfortunately, the non-vectorial and discrete nature of trees makes it challenging to construct functions with tree-formed output, complicating tasks such as optimization or time series prediction. Autoencoders address this challenge by mapping trees to a vectorial latent space, where tasks are easier to solve, and then mapping the solution back to a tree structure. However, existing autoencoding approaches for tree data fail to take the specific grammatical structure of tree domains into account and rely on deep learning, thus requiring large training datasets and long training times. In this paper, we propose tree echo state autoencoders (TES-AE), which are guided by a tree grammar and can be trained within seconds by virtue of reservoir computing. In our evaluation on three datasets, we demonstrate that our proposed approach is not only much faster than a state-of-the-art deep learning autoencoding approach (D-VAE) but also has less autoencoding error if little data and time is given.

We study a multi-round welfare-maximising mechanism design problem, where, on each round, a mechanism assigns an allocation each to a set of agents and charges them a price. Then the agents report their realised (stochastic) values back to the mechanism. This is motivated by applications in cloud markets and online advertising where an agent may know her value for an allocation only after experiencing it. The distribution of these values is unknown to the agent beforehand which necessitates learning them over multiple rounds while simultaneously attempting to find the socially optimal set of allocations. Our focus is on designing truthful and individually rational mechanisms which imitate the classical VCG mechanism in the long run. To that end, we define three notions of regret for the welfare, the individual utilities of each agent (value minus price) and that of the mechanism (revenue minus cost). We show that these three terms are interdependent via an $\Omega(T^{2/3})$ lower bound for the maximum of these three terms after $T$ rounds of allocations. We describe a family of anytime algorithms which achieve this rate. The proposed framework provides flexibility to control the pricing scheme so as to trade-off between the agent and seller regrets, and additionally to control the degree of truthfulness and individual rationality.

With a few lines of code, DeepPurpose generates drug candidates based on aggregating five pretrained state-of-the-art models while offering flexibility for users to train their own models with 15 drug/target encodings and 50 novel architectures. We demonstrated DeepPurpose using case studies, including repurposing for COVID-19 where promising candidates under trials are ranked high in our results. Drug repurposing is about investigating existing drugs for new therapeutic purposes which can potentially speed up drug development 1 . With a large number of existing drugs, it is important to quickly and accurately identify promising candidates for new indications. Especially in facing COVID-19 pandemic today, drug repurposing become particularly relevant as a potentially much faster way to discover effective and safe drugs for treating COVID-19. Deep learning has recently demonstrated its superior performance than classic methods to assist computational drug discovery 2, 3, thanks to its expressive power in extracting, processing and extrapolating patterns in molecular data.

Collaborative multi-agent reinforcement learning is an important sub-field of the multiagent reinforcement learning (MARL), where the agents learn to coordinate to achieve joint success. It has wide applications in traffic control [Kuyer et al., 2008], autonomous driving [Shalev-Shwartz et al., 2016] and smart grid [Yang et al., 2018]. To learn a coordination, the interactions between agents are indispensable. For instance, humans can reason about other's behaviors or know other peoples' intentions through communication and then determine an effective coordination plan. However, how to design a mechanism of such interaction in a principled way and at the same time solve the large scale real-world applications is still a challenging problem. Recently, there is a surge of interest in solving the collaborative MARL problem [Foerster et al., 2018, Qu et al., 2019, Lowe et al., 2017]. Among them, joint policy approaches have demonstrated their superiority [Rashid et al., 2018, Sunehag et al., 2018, Oliehoek et al., 2016]. A straightforward approach is to replace the action in the single-agent reinforcement learning by the joint action a (a 1, a 2,..., a N), while it obviously suffers from the issue of the exponentially large action space.

Recent advancements in Neural Architecture Search(NAS) resulted in finding new state-of-the-art Artificial Neural Network (ANN) solutions for tasks like image classification, object detection, or semantic segmentation without substantial human supervision. In this paper, we focus on exploring NAS for a dense prediction task that is image denoising. Due to a costly training procedure, most NAS solutions for image enhancement rely on reinforcement learning or evolutionary algorithm exploration, which usually take weeks (or even months) to train. Therefore, we introduce a new efficient implementation of various superkernel techniques that enable fast (6-8 RTX2080 GPU hours) single-shot training of models for dense predictions. We demonstrate the effectiveness of our method on the SIDD+ benchmark for image denoising.

Knowledge Distillation (KD) is a common method for transferring the ``knowledge'' learned by one machine learning model (the \textit{teacher}) into another model (the \textit{student}), where typically, the teacher has a greater capacity (e.g., more parameters or higher bit-widths). To our knowledge, existing methods overlook the fact that although the student absorbs extra knowledge from the teacher, both models share the same input data -- and this data is the only medium by which the teacher's knowledge can be demonstrated. Due to the difference in model capacities, the student may not benefit fully from the same data points on which the teacher is trained. On the other hand, a human teacher may demonstrate a piece of knowledge with individualized examples adapted to a particular student, for instance, in terms of her cultural background and interests. Inspired by this behavior, we design data augmentation agents with distinct roles to facilitate knowledge distillation. Our data augmentation agents generate distinct training data for the teacher and student, respectively. We find empirically that specially tailored data points enable the teacher's knowledge to be demonstrated more effectively to the student. We compare our approach with existing KD methods on training popular neural architectures and demonstrate that role-wise data augmentation improves the effectiveness of KD over strong prior approaches. The code for reproducing our results can be found at https://github.com/bigaidream-projects/role-kd

Combining model-based and model-free learning systems has been shown to improve the sample efficiency of learning to perform complex robotic tasks. However, dual-system approaches fail to consider the reliability of the learned model when it is applied to make multiple-step predictions, resulting in a compounding of prediction errors and performance degradation. In this paper, we present a novel dual-system motor learning approach where a meta-controller arbitrates online between model-based and model-free decisions based on an estimate of the local reliability of the learned model. The reliability estimate is used in computing an intrinsic feedback signal, encouraging actions that lead to data that improves the model. Our approach also integrates arbitration with imagination where a learned latent-space model generates imagined experiences, based on its local reliability, to be used as additional training data. We evaluate our approach against baseline and state-of-the-art methods on learning vision-based robotic grasping in simulation and real world. The results show that our approach outperforms the compared methods and learns near-optimal grasping policies in dense- and sparse-reward environments.

Neural networks have become a powerful tool in pattern recognition and part of their success is due to generalization from using large datasets. However, unlike other domains, time series classification datasets are often small. In order to address this problem, we propose a novel time series data augmentation called guided warping. While many data augmentation methods are based on random transformations, guided warping exploits the element alignment properties of Dynamic Time Warping (DTW) and shapeDTW, a high-level DTW method based on shape descriptors, to deterministically warp sample patterns. In this way, the time series are mixed by warping the features of a sample pattern to match the time steps of a reference pattern. Furthermore, we introduce a discriminative teacher in order to serve as a directed reference for the guided warping. We evaluate the method on all 85 datasets in the 2015 UCR Time Series Archive with a deep convolutional neural network (CNN) and a recurrent neural network (RNN). The code with an easy to use implementation can be found at https://github.com/uchidalab/time_series_augmentation .