Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Recent advancements in deep neural networks for graph-structured data have led to state-of-the-art performance on recommender system benchmarks. However, making these methods practical and scalable to web-scale recommendation tasks with billions of items and hundreds of millions of users remains an unsolved challenge. Here we describe a large-scale deep recommendation engine that we developed and deployed at Pinterest. We develop a data-efficient Graph Convolutional Network (GCN) algorithm, which combines efficient random walks and graph convolutions to generate embeddings of nodes (i.e., items) that incorporate both graph structure as well as node feature information. Compared to prior GCN approaches, we develop a novel method based on highly efficient random walks to structure the convolutions and design a novel training strategy that relies on harder-and-harder training examples to improve robustness and convergence of the model. We also develop an efficient MapReduce model inference algorithm to generate embeddings using a trained model. Overall, we can train on and embed graphs that are four orders of magnitude larger than typical GCN implementations. We show how GCN embeddings can be used to make high-quality recommendations in various settings at Pinterest, which has a massive underlying graph with 3 billion nodes representing pins and boards, and 17 billion edges. According to offline metrics, user studies, as well as A/B tests, our approach generates higher-quality recommendations than comparable deep learning based systems. To our knowledge, this is by far the largest application of deep graph embeddings to date and paves the way for a new generation of web-scale recommender systems based on graph convolutional architectures.

Graph Convolutional Neural Networks for Web-Scale Recommender Systems

https://www.cell.com/trends/neurosciences/pdf/S0166-2236(09)00153-2.pdf

Molecular dissection of reactive astrogliosis and glial scar formation.

Matrix Factorization Techniques for Recommender Systems

Theranostics: Combining Imaging and Therapy

Developing a Financial Inclusion Index for India

The adjustment of X-linked gene expression to the X chromosome copy number (dosage compensation [DC]) has been widely studied as a model of chromosome-wide gene regulation. In Caenorhabditis elegans, DC is achieved by twofold down-regulation of gene expression from both Xs in hermaphrodites. We show that in males, the single X chromosome interacts with nuclear pore proteins, while in hermaphrodites, the DC complex (DCC) impairs this interaction and alters X localization. Our results put forward a structural model of DC in which X-specific sequences locate the X chromosome in transcriptionally active domains in males, while the DCC prevents this in hermaphrodites.

/pdf/differential-spatial-and-structural-organization-of-the-x-453fauzesf.pdf

Differential spatial and structural organization of the X chromosome underlies dosage compensation in C. elegans

For the most part, normal epithelial cells do not disseminate to other parts of the body and proliferate, as do metastatic cells. Presumably, a class of molecules-termed metastasis suppressors-are involved in this homeostatic control. Metastasis suppressors are, by definition, cellular factors that, when re-expressed in metastatic cells, functionally inhibit metastasis without significantly inhibiting tumor growth. In this brief review, we catalog known metastasis suppressors, what is known about their mechanism(s) of action, and experimental and clinical associations to date.

/pdf/metastasis-suppressors-in-breast-cancers-mechanistic-47liph80wo.pdf

Metastasis suppressors in breast cancers: Mechanistic insights and clinical potential

We formulate the loop-free, binary superoptimization task as a stochastic search problem The competing constraints of transformation correctness and performance improvement are encoded as terms in a cost function, and a Markov Chain Monte Carlo sampler is used to rapidly explore the space of all possible programs to find one that is an optimization of a given target program Although our method sacrifices com- pleteness, the scope of programs we are able to reason about, and the quality of the programs we produce, far exceed those of existing superoptimizers Beginning from binaries com- piled by llvm -O0 for 64-bit X86, our prototype implemen- tation, STOKE, is able to produce programs which either match or outperform the code sequences produced by gcc with full optimizations enabled, and, in some cases, expert handwritten assembly

Stochastic Superoptimization

We show how a test suite for a sequential program can be profitably used to construct a termination proof. In particular, we describe an algorithm TpT for proving termination of a program based on information derived from testing it. TpT iteratively calls two phases: (a) an infer phase, and (b) a validate phase. In the infer phase, machine learning, in particular, linear regression is used to efficiently compute a candidate loop bound for every loop in the program. These loop bounds are verified for correctness by an off-the-shelf checker. If a loop bound is invalid, then the safety checker provides a test or a counterexample that is used to generate more data which is subsequently used by the next infer phase to compute better estimates for loop bounds. On the other hand, if all loop bounds are valid, then we have a proof of termination. We also describe a simple extension to our approach that allows us to infer polynomial loop bounds automatically. We have evaluated TpT on two benchmark sets, micro-benchmarks obtained from recent literature on program termination, and Windows device drivers. Our results are promising -- on the micro-benchmarks, we show that TpT is able to prove termination on 15% more benchmarks than any previously known technique, and our evaluation on Windows device drivers demonstrates TpT's ability to analyze and scale to real world applications.

/pdf/termination-proofs-from-tests-4pixt32ijk.pdf

Rahul Sharma

Papers

Developing a Financial Inclusion Index for India

Differential spatial and structural organization of the X chromosome underlies dosage compensation in C. elegans

Metastasis suppressors in breast cancers: Mechanistic insights and clinical potential

Stochastic Superoptimization

Termination proofs from tests