Interactive Information Retrieval (IIR) and Reinforcement Learning (RL) share many commonalities, including an agent who learns while interacts, a long-term and complex goal, and an algorithm that explores and adapts. To successfully apply RL methods to IIR, one challenge is to obtain sufficient relevance labels to train the RL agents, which are infamously known as sample inefficient. However, in a text corpus annotated for a given query, it is not the relevant documents but the irrelevant documents that predominate. This would cause very unbalanced training experiences for the agent and prevent it from learning any policy that is effective. Our paper addresses this issue by using domain randomization to synthesize more relevant documents for the training. Our experimental results on the Text REtrieval Conference (TREC) Dynamic Domain (DD) 2017 Track show that the proposed method is able to boost an RL agent's learning effectiveness by 22\% in dealing with unseen situations.

Training deep neural networks (DNNs) in large-cluster computing environments is increasingly necessary, as networks grow in size and complexity. Local memory and processing limitations require robust data and model parallelism for crossing compute node boundaries. We propose a linear-algebraic approach to model parallelism in deep learning, which allows parallel distribution of any tensor in the DNN. Rather than rely on automatic differentiation tools, which do not universally support distributed memory parallelism models, we show that parallel data movement operations, e.g., broadcast, sum-reduce, and halo exchange, are linear operators, and by defining the relevant spaces and inner products, we manually develop the adjoint, or backward, operators required for gradient-based training of DNNs. We build distributed DNN layers using these parallel primitives, composed with sequential layer implementations, and demonstrate their application by building and training a distributed DNN using DistDL, a PyTorch and MPI-based distributed deep learning toolkit.

We study graph-based Laplacian semi-supervised learning at low labeling rates. Laplacian learning uses harmonic extension on a graph to propagate labels. At very low label rates, Laplacian learning becomes degenerate and the solution is roughly constant with spikes at each labeled data point. Previous work has shown that this degeneracy occurs when the number of labeled data points is finite while the number of unlabeled data points tends to infinity. In this work we allow the number of labeled data points to grow to infinity with the number of labels. Our results show that for a random geometric graph with length scale $\varepsilon>0$ and labeling rate $\beta>0$, if $\beta \ll\varepsilon^2$ then the solution becomes degenerate and spikes form, and if $\beta\gg \varepsilon^2$ then Laplacian learning is well-posed and consistent with a continuum Laplace equation. Furthermore, in the well-posed setting we prove quantitative error estimates of $O(\varepsilon\beta^{-1/2})$ for the difference between the solutions of the discrete problem and continuum PDE, up to logarithmic factors. We also study $p$-Laplacian regularization and show the same degeneracy result when $\beta \ll \varepsilon^p$. The proofs of our well-posedness results use the random walk interpretation of Laplacian learning and PDE arguments, while the proofs of the ill-posedness results use $\Gamma$-convergence tools from the calculus of variations. We also present numerical results on synthetic and real data to illustrate our results.

We present an approach to synthesizing new graph structures from empirically specified distributions. The generative model is an auto-decoder that learns to synthesize graphs from latent codes. The graph synthesis model is learned jointly with an empirical distribution over the latent codes. Graphs are synthesized using self-attention modules that are trained to identify likely connectivity patterns. Graph-based normalizing flows are used to sample latent codes from the distribution learned by the auto-decoder. The resulting model combines accuracy and scalability. On benchmark datasets of large graphs, the presented model outperforms the state of the art by a factor of 1.5 in mean accuracy and average rank across at least three different graph statistics, with a 2x speedup during inference.

In past few years, linear rectified unit activation functions have shown its significance in the neural networks, surpassing the performance of sigmoid activations. RELU (Nair & Hinton, 2010), ELU (Clevert et al., 2015), PRELU (He et al., 2015), LRELU (Maas et al., 2013), SRELU (Jin et al., 2016), ThresholdedRELU, all these linear rectified activation functions have its own significance over others in some aspect. Most of the time these activation functions suffer from bias shift problem due to non-zero output mean, and high weight update problem in deep complex networks due to unit gradient, which results in slower training, and high variance in model prediction respectively. In this paper, we propose, "Thresholded exponential rectified linear unit" (TERELU) activation function that works better in alleviating in overfitting: large weight update problem. Along with alleviating overfitting problem, this method also gives good amount of non-linearity as compared to other linear rectifiers. We will show better performance on the various datasets using neural networks, considering TERELU activation method compared to other activations.

Personal privacy information may be exposed with the unprecedented availability of datasets, so there is increasing requirement that statistical analysis of such datasets should protect individual privacy. As [6] describes, differential privacy addresses the paradox of learning nothing about an individual while learning useful information about a population. Over the past few years, differential privacy has been investigated in machine learning [1] and has been applied in the real world, see for example [8]. Recently, [3] formulates a general lower bound argument for minimax risks with differential privacy constraints, and applies this argument to high-dimensional mean estimation and linear regression problems. In this paper, three privacy preserving methods are proposed for median regression, which is a special case of quantile regression. Quantile regression was first introduced in [12], which aims to estimate and conduct inference about conditional quantile functions. In recent years, quantile regression has become a comprehensive method for statistical analysis of response models and it has been widely used in reality, such as survival analysis and economics, see for example, [14], [20] and [15]. The fact that the median regression takes least absolute deviation as its objective function to estimate parameters has been known among statisticians [12].

Against this background, we investigated in how far the inclusion of satellite images improves the predictive accuracy of real estate pricing models and how one can explain the predictions of these models by identifying discriminative visual features between high and low price houses. For our proof-of-concept, we use real estate data from Asheville, North Carolina [1]. The Bing Maps API is used to obtain satellite images [5] with zoom level 16, depicting 600 by 600 meters around the real estate property. We trained multiple CNNs containing tabular data as well as image data as inputs and the observed house price as the output (see Figure 1). The results show that image data improves the prediction performance of house pricing models (see Table 1).

In this work we propose a machine learning model for depression detection from transcribed clinical interviews. Depression is a mental disorder that impacts not only the subject's mood but also the use of language. To this end we use a Hierarchical Attention Network to classify interviews of depressed subjects. We augment the attention layer of our model with a conditioning mechanism on linguistic features, extracted from affective lexica. Our analysis shows that individuals diagnosed with depression use affective language to a greater extent than not-depressed. Our experiments show that external affective information improves the performance of the proposed architecture in the General Psychotherapy Corpus and the DAIC-WoZ 2017 depression datasets, achieving state-of-the-art 71.6 and 68.6 F1 scores respectively.

Physicians taking care of patients with coronavirus disease (COVID-19) have described different changes in routine blood parameters. However, these changes, hinder them from performing COVID-19 diagnosis. We constructed a machine learning predictive model for COVID-19 diagnosis. The model was based and cross-validated on the routine blood tests of 5,333 patients with various bacterial and viral infections, and 160 COVID-19-positive patients. We selected operational ROC point at a sensitivity of 81.9% and specificity of 97.9%. The cross-validated area under the curve (AUC) was 0.97. The five most useful routine blood parameters for COVID19 diagnosis according to the feature importance scoring of the XGBoost algorithm were MCHC, eosinophil count, albumin, INR, and prothrombin activity percentage. tSNE visualization showed that the blood parameters of the patients with severe COVID-19 course are more like the parameters of bacterial than viral infection. The reported diagnostic accuracy is at least comparable and probably complementary to RT-PCR and chest CT studies. Patients with fever, cough, myalgia, and other symptoms can now have initial routine blood tests assessed by our diagnostic tool. All patients with a positive COVID-19 prediction would then undergo standard RT-PCR studies to confirm the diagnosis. We believe that our results present a significant contribution to improvements in COVID-19 diagnosis.

We introduce Wasserstein Adversarial Proximal Policy Optimization (WAPPO), a novel algorithm for visual transfer in Reinforcement Learning that explicitly learns to align the distributions of extracted features between a source and target task. WAPPO approximates and minimizes the Wasserstein-1 distance between the distributions of features from source and target domains via a novel Wasserstein Confusion objective. WAPPO outperforms the prior state-of-the-art in visual transfer and successfully transfers policies across Visual Cartpole and two instantiations of 16 OpenAI Procgen environments.