The approval success rate of drug candidates is very low with the majority of failure due to safety and efficacy. Increasingly available high dimensional information on targets, drug molecules and indications provides an opportunity for ML methods to integrate multiple data modalities and better predict clinically promising drug targets. Notably, drug targets with human genetics evidence are shown to have better odds to succeed. However, a recent tensor factorization-based approach found that additional information on targets and indications might not necessarily improve the predictive accuracy. Here we revisit this approach by integrating different types of human genetics evidence collated from publicly available sources to support each target-indication pair. We use Bayesian tensor factorization to show that models incorporating all available human genetics evidence (rare disease, gene burden, common disease) modestly improves the clinical outcome prediction over models using single line of genetics evidence. We provide additional insight into the relative predictive power of different types of human genetics evidence for predicting the success of clinical outcomes.

Gunasekar et al. (2017) observed We study the implicit regularization effects of that for matrix factorization when there are no constraints on deep learning in tensor factorization. While implicit the rank, the solution of the optimization problem via gradient regularization in deep matrix and'shallow' descent turns out to be a low-rank matrix. Furthermore, tensor factorization via linear and certain type of they conjectured that, with small enough learning rate and non-linear neural networks promotes low-rank solutions initialization, gradient descent on full-dimensional matrix with at most quadratic growth, we show factorization converges to the solution with minimal nuclear that its effect in deep tensor factorization grows norm. Arora et al. (2019) and Razin & Cohen (2020) extended polynomially with the depth of the network. This the analysis to deep matrix factorization and showed provides a remarkably faithful description of the in this case that implicit regularization of gradient descent observed experimental behaviour. Using numerical cannot be formulated as a norm-minimization problem. By experiments, we demonstrate the benefits of studying the dynamics of gradient descent, they found theoretically this implicit regularization in yielding a more accurate and experimentally that it instead promotes sparsity estimation and better convergence properties. of the singular values of the learned matrix, indicating that implicit regularization in deep learning has to be studied from a dynamical point of view. Moreover, Razin et al. (2021) studied implicit regularization in'shallow' tensor

In this note we introduce a novel clustering preserving transformation of cluster sets obtained from k-means algorithm. It may be considered as a contribution towards formulation of clustering axiomatic system. From the practical point of view, this clustering preserving transformation can be used for purposes of: generating new labeled datasets from existent ones, which may be of use in testing algorithms from k-means family in their stability on cluster perturbations which d not change the theoretical clustering, generating new labeled datasets from existent ones, obfuscating sensitive data From the theoretical standpoint, the contribution of this paper consists in proposing a less rigid cluster preserving transformation than centric consistency, known so far as the only cluster preserving transformation for k-means family of algorithms.

During the last decade, Neural Networks (NNs) have proved to be extremely effective tools in many fields of engineering, including autonomous vehicles, medical diagnosis and search engines, and even in art creation. Indeed, NNs often decisively outperform traditional algorithms. One area that is only recently attracting significant interest is using NNs for designing numerical solvers, particularly for discretized partial differential equations. Several recent papers have considered employing NNs for developing multigrid methods, which are a leading computational tool for solving discretized partial differential equations and other sparse-matrix problems. We extend these new ideas, focusing on so-called relaxation operators (also called smoothers), which are an important component of the multigrid algorithm that has not yet received much attention in this context. We explore an approach for using NNs to learn relaxation parameters for an ensemble of diffusion operators with random coefficients, for Jacobi type smoothers and for 4Color GaussSeidel smoothers. The latter yield exceptionally efficient and easy to parallelize Successive Over Relaxation (SOR) smoothers. Moreover, this work demonstrates that learning relaxation parameters on relatively small grids using a two-grid method and Gelfand's formula as a loss function can be implemented easily. These methods efficiently produce nearly-optimal parameters, thereby significantly improving the convergence rate of multigrid algorithms on large grids.

The increasing scale of model size and continuous improvement of performance herald the arrival of the Big Model era. In this report, we explore what and how the big model training works by diving into training objectives and training methodologies. Specifically,training objectives describe how to leverage web-scale data to develop extremely capable and incredibly large models based on self-supervised learning, and training methodologies which are based on distributed training describe how to make big model training a reality. We summarize the existing training methodologies into three main categories: training parallelism, memory-saving technologies, and model sparsity design. Training parallelism can be categorized into data, pipeline, and tensor parallelism according to the dimension of parallelism that takes place. Memory-saving technologies are orthogonal and complementary to training parallelism. And model sparsity design further scales up the model size with a constant computational cost. A continuously updated paper list of big model training is provided at https://github.com/qhliu26/BM-Training.

People leverage group discussions to collaborate in order to solve complex tasks, e.g. in project meetings or hiring panels. By doing so, they engage in a variety of conversational strategies where they try to convince each other of the best approach and ultimately reach a decision. In this work, we investigate methods for detecting what makes someone change their mind. To this end, we leverage a recently introduced dataset containing group discussions of people collaborating to solve a task. To find out what makes someone change their mind, we incorporate various techniques such as neural text classification and language-agnostic change point detection. Evaluation of these methods shows that while the task is not trivial, the best way to approach it is using a language-aware model with learning-to-rank training. Finally, we examine the cues that the models develop as indicative of the cause of a change of mind.

Hierarchical models represent a challenging setting for inference algorithms. MCMC methods struggle to scale to large models with many local variables and observations, and variational inference (VI) may fail to provide accurate approximations due to the use of simple variational families. Some variational methods (e.g. importance weighted VI) integrate Monte Carlo methods to give better accuracy, but these tend to be unsuitable for hierarchical models, as they do not allow for subsampling and their performance tends to degrade for high dimensional models. We propose a new family of variational bounds for hierarchical models, based on the application of tightening methods (e.g. importance weighting) separately for each group of local random variables. We show that our approach naturally allows the use of subsampling to get unbiased gradients, and that it fully leverages the power of methods that build tighter lower bounds by applying them independently in lower dimensional spaces, leading to better results and more accurate posterior approximations than relevant baselines.

Unsupervised domain adaptation (UDA) transfers knowledge from a label-rich source domain to a different but related fully-unlabeled target domain. To address the problem of domain shift, more and more UDA methods adopt pseudo labels of the target samples to improve the generalization ability on the target domain. However, inaccurate pseudo labels of the target samples may yield suboptimal performance with error accumulation during the optimization process. Moreover, once the pseudo labels are generated, how to remedy the generated pseudo labels is far from explored. In this paper, we propose a novel approach to improve the accuracy of the pseudo labels in the target domain. It first generates coarse pseudo labels by a conventional UDA method. Then, it iteratively exploits the intra-class similarity of the target samples for improving the generated coarse pseudo labels, and aligns the source and target domains with the improved pseudo labels. The accuracy improvement of the pseudo labels is made by first deleting dissimilar samples, and then using spanning trees to eliminate the samples with the wrong pseudo labels in the intra-class samples. We have applied the proposed approach to several conventional UDA methods as an additional term. Experimental results demonstrate that the proposed method can boost the accuracy of the pseudo labels and further lead to more discriminative and domain invariant features than the conventional baselines.

Given the rapidly changing machine learning environments and expensive data labeling, semi-supervised domain adaptation (SSDA) is imperative when the labeled data from the source domain is statistically different from the partially labeled data from the target domain. Most prior SSDA research is centrally performed, requiring access to both source and target data. However, data in many fields nowadays is generated by distributed end devices. Due to privacy concerns, the data might be locally stored and cannot be shared, resulting in the ineffectiveness of existing SSDA research. This paper proposes an innovative approach to achieve SSDA over multiple distributed and confidential datasets, named by Federated Semi-Supervised Domain Adaptation (FSSDA). FSSDA integrates SSDA with federated learning based on strategically designed knowledge distillation techniques, whose efficiency is improved by performing source and target training in parallel. Moreover, FSSDA controls the amount of knowledge transferred across domains by properly selecting a key parameter, i.e., the imitation parameter. Further, the proposed FSSDA can be effectively generalized to multi-source domain adaptation scenarios. Extensive experiments are conducted to demonstrate the effectiveness and efficiency of FSSDA design.

We present a novel hybrid algorithm for training Deep Neural Networks that combines the state-of-the-art Gradient Descent (GD) method with a Mixed Integer Linear Programming (MILP) solver, outperforming GD and variants in terms of accuracy, as well as resource and data efficiency for both regression and classification tasks. Our GD+Solver hybrid algorithm, called GDSolver, works as follows: given a DNN $D$ as input, GDSolver invokes GD to partially train $D$ until it gets stuck in a local minima, at which point GDSolver invokes an MILP solver to exhaustively search a region of the loss landscape around the weight assignments of $D$'s final layer parameters with the goal of tunnelling through and escaping the local minima. The process is repeated until desired accuracy is achieved. In our experiments, we find that GDSolver not only scales well to additional data and very large model sizes, but also outperforms all other competing methods in terms of rates of convergence and data efficiency. For regression tasks, GDSolver produced models that, on average, had 31.5% lower MSE in 48% less time, and for classification tasks on MNIST and CIFAR10, GDSolver was able to achieve the highest accuracy over all competing methods, using only 50% of the training data that GD baselines required.