This paper addresses the meta-learning problem in sparse linear regression with infinite tasks. We assume that the learner can access several similar tasks. The goal of the learner is to transfer knowledge from the prior tasks to a similar but novel task. For p parameters, size of the support set k , and l samples per task, we show that T \in O (( k log(p) ) /l ) tasks are sufficient in order to recover the common support of all tasks. With the recovered support, we can greatly reduce the sample complexity for estimating the parameter of the novel task, i.e., l \in O (1) with respect to T and p . We also prove that our rates are minimax optimal. A key difference between meta-learning and the classical multi-task learning, is that meta-learning focuses only on the recovery of the parameters of the novel task, while multi-task learning estimates the parameter of all tasks, which requires l to grow with T . Instead, our efficient meta-learning estimator allows for l to be constant with respect to T (i.e., few-shot learning).

We study generalised linear regression and classification for a synthetically generated dataset encompassing different problems of interest, such as learning with random features, neural networks in the lazy training regime, and the hidden manifold model. We consider the high-dimensional regime and using the replica method from statistical physics, we provide a closed-form expression for the asymptotic generalisation performance in these problems, valid in both the under- and over-parametrised regimes and for a broad choice of generalised linear model loss functions. In particular, we show how to obtain analytically the so-called double descent behaviour for logistic regression with a peak at the interpolation threshold, we illustrate the superiority of orthogonal against random Gaussian projections in learning with random features, and discuss the role played by correlations in the data generated by the hidden manifold model. Beyond the interest in these particular problems, the theoretical formalism introduced in this manuscript provides a path to further extensions to more complex tasks.

Knowledge distillation (KD) is one of the most potent ways for model compression. The key idea is to transfer the knowledge from a deep teacher model (T) to a shallower student (S). However, existing methods suffer from performance degradation due to the substantial gap between the learning capacities of S and T. To remedy this problem, this work proposes Residual Knowledge Distillation (RKD), which further distills the knowledge by introducing an assistant (A). Specifically, S is trained to mimic the feature maps of T, and A aids this process by learning the residual error between them. In this way, S and A complement with each other to get better knowledge from T. Furthermore, we devise an effective method to derive S and A from a given model without increasing the total computational cost. Extensive experiments show that our approach achieves appealing results on popular classification datasets, CIFAR-100 and ImageNet, surpassing state-of-the-art methods.

We introduce a new and completely online contextual bandit algorithm called Gated Linear Contextual Bandits (GLCB). This algorithm is based on Gated Linear Networks (GLNs), a recently introduced deep learning architecture with properties well-suited to the online setting. Leveraging data-dependent gating properties of the GLN we are able to estimate prediction uncertainty with effectively zero algorithmic overhead. We empirically evaluate GLCB compared to 9 state-of-the-art algorithms that leverage deep neural networks, on a standard benchmark suite of discrete and continuous contextual bandit problems. GLCB obtains median first-place despite being the only online method, and we further support these results with a theoretical study of its convergence properties.

Clayton Christensen, author of The Innovator's Dilemma and a Harvard Business School professor, died last month. Normally, this word suggests a negative connotation. The talkative student was disruptive to the rest of the class, or the reckless driver was disruptive to the flow of traffic. Dictionary.com lists the following words as related to disruptive: upsetting, disturbing, troublesome, rowdy, troublemaking. Yet this word is used routinely in society and business, often with a positive, or at least neutral, connotation.

The main pillar of the plan is focused on accelerating Mexico's digital transformation through democratizing the access to technology. The company announced plans to establish a new cloud datacenter region in Mexico to deliver its intelligent and trusted cloud services to serve Mexico's public entities, organizations and Mexican society, including Microsoft Azure, Office 365, Dynamics 365 and the Power Platform. This datacenter region is an important part of Microsoft's $1.1 billion investment plan in Mexico over the next five years. The plan also includes a robust education and skilling program with different initiatives the first one being the creation of three laboratories and a virtual classroom, in collaboration with public universities to create an education platform for digital skills, to expand employability in future generations. The first initiative of the commitment to apply artificial intelligence to create societal impact is an investment in the project "Artificial Intelligence to Monitor Pelagic Sharks in the Mexican Pacific Ocean" (Shark ID), focused on the conservation of Mako shark species, driven by Mexico Azul, as part of the initiative AI for Earth, creating societal impact.

Wharton Online's newest program based on best-selling book "A Human's Guide to Machine Intelligence" Artificial intelligence (AI) is embedded in nearly every aspect of daily life, from entertainment (e.g. To address the risks, opportunities and challenges of implementing artificial intelligence into business practice, the Wharton School of the University of Pennsylvania is pleased to announce a new online program: Artificial Intelligence for Business. This four-week program, Wharton's first public offering to address AI, can help working professionals successfully navigate today's technological changes so they can create the innovations of tomorrow. Based on the best-selling book, A Human's Guide to Machine Intelligence, by acclaimed Wharton professor Kartik Hosanagar, the Artificial Intelligence for Business program is designed to provide learners with insights into both established and emerging developments in AI, Big Data, Machine Learning, and the operational changes AI will bring. The lessons within this course are applicable to multiple industries and dynamic markets.

We study online learning settings in which experts act strategically to maximize their influence on the learning algorithm's predictions by potentially misreporting their beliefs about a sequence of binary events. Our goal is twofold. First, we want the learning algorithm to be no-regret with respect to the best fixed expert in hindsight. Second, we want incentive compatibility, a guarantee that each expert's best strategy is to report his true beliefs about the realization of each event. To achieve this goal, we build on the literature on wagering mechanisms, a type of multi-agent scoring rule. We provide algorithms that achieve no regret and incentive compatibility for myopic experts for both the full and partial information settings. In experiments on datasets from FiveThirtyEight, our algorithms have regret comparable to classic no-regret algorithms, which are not incentive-compatible. Finally, we identify an incentive-compatible algorithm for forward-looking strategic agents that exhibits diminishing regret in practice.

Machine learning pipelines often rely on optimization procedures to make discrete decisions (e.g. sorting, picking closest neighbors, finding shortest paths or optimal matchings). Although these discrete decisions are easily computed in a forward manner, they cannot be used to modify model parameters using first-order optimization techniques because they break the back-propagation of computational graphs. In order to expand the scope of learning problems that can be solved in an end-to-end fashion, we propose a systematic method to transform a block that outputs an optimal discrete decision into a differentiable operation. Our approach relies on stochastic perturbations of these parameters, and can be used readily within existing solvers without the need for ad hoc regularization or smoothing. These perturbed optimizers yield solutions that are differentiable and never locally constant. The amount of smoothness can be tuned via the chosen noise amplitude, whose impact we analyze. The derivatives of these perturbed solvers can be evaluated efficiently. We also show how this framework can be connected to a family of losses developed in structured prediction, and describe how these can be used in unsupervised and supervised learning, with theoretical guarantees. We demonstrate the performance of our approach on several machine learning tasks in experiments on synthetic and real data.

Seed scheduling is a prominent factor in determining the yields of hybrid fuzzing. Existing hybrid fuzzers schedule seeds based on fixed heuristics that aim to predict input utilities. However, such heuristics are not generalizable as there exists no one-size-fits-all rule applicable to different programs. They may work well on the programs from which they were derived, but not others. To overcome this problem, we design a Machine learning-Enhanced hybrid fUZZing system (MEUZZ), which employs supervised machine learning for adaptive and generalizable seed scheduling. MEUZZ determines which new seeds are expected to produce better fuzzing yields based on the knowledge learned from past seed scheduling decisions made on the same or similar programs. MEUZZ's learning is based on a series of features extracted via code reachability and dynamic analysis, which incurs negligible runtime overhead (in microseconds). Moreover, MEUZZ automatically infers the data labels by evaluating the fuzzing performance of each selected seed. As a result, MEUZZ is generally applicable to, and performs well on, various kinds of programs. Our evaluation shows MEUZZ significantly outperforms the state-of-the-art grey-box and hybrid fuzzers, achieving 27.1% more code coverage than QSYM. The learned models are reusable and transferable, which boosts fuzzing performance by 7.1% on average and improves 68% of the 56 cross-program fuzzing campaigns. MEUZZ discovered 47 deeply hidden and previously unknown bugs--with 21 confirmed and fixed by the developers--when fuzzing 8 well-tested programs with the same configurations as used in previous work.