The author's preface gives an outline: "This book is about weakconvergence methods in metric spaces, with applications sufficient to show their power and utility. The Introduction motivates the definitions and indicates how the theory will yield solutions to problems arising outside it. Chapter 1 sets out the basic general theorems, which are then specialized in Chapter 2 to the space C[0, l ] of continuous functions on the unit interval and in Chapter 3 to the space D [0, 1 ] of functions with discontinuities of the first kind. The results of the first three chapters are used in Chapter 4 to derive a variety of limit theorems for dependent sequences of random variables. " The book develops and expands on Donsker's 1951 and 1952 papers on the invariance principle and empirical distributions. The basic random variables remain real-valued although, of course, measures on C[0, l ] and D[0, l ] are vitally used. Within this framework, there are various possibilities for a different and apparently better treatment of the material. More of the general theory of weak convergence of probabilities on separable metric spaces would be useful. Metrizability of the convergence is not brought up until late in the Appendix. The close relation of the Prokhorov metric and a metric for convergence in probability is (hence) not mentioned (see V. Strassen, Ann. Math. Statist. 36 (1965), 423-439; the reviewer, ibid. 39 (1968), 1563-1572). This relation would illuminate and organize such results as Theorems 4.1, 4.2 and 4.4 which give isolated, ad hoc connections between weak convergence of measures and nearness in probability. In the middle of p. 16, it should be noted that C*(S) consists of signed measures which need only be finitely additive if 5 is not compact. On p. 239, where the author twice speaks of separable subsets having nonmeasurable cardinal, he means "discrete" rather than "separable." Theorem 1.4 is Ulam's theorem that a Borel probability on a complete separable metric space is tight. Theorem 1 of Appendix 3 weakens completeness to topological completeness. After mentioning that probabilities on the rationals are tight, the author says it is an

Convergence of probability measures

In the last years, Artificial Intelligence (AI) has achieved a notable momentum that may deliver the best of expectations over many application sectors across the field. For this to occur, the entire community stands in front of the barrier of explainability, an inherent problem of AI techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI. Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is acknowledged as a crucial feature for the practical deployment of AI models. This overview examines the existing literature in the field of XAI, including a prospect toward what is yet to be reached. We summarize previous efforts to define explainability in Machine Learning, establishing a novel definition that covers prior conceptual propositions with a major focus on the audience for which explainability is sought. We then propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at Deep Learning methods for which a second taxonomy is built. This literature analysis serves as the background for a series of challenges faced by XAI, such as the crossroads between data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence, namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to XAI with a reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI.

Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g. service provider), while keeping the training data decentralized. FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches. Motivated by the explosive growth in FL research, this paper discusses recent advances and presents an extensive collection of open problems and challenges.

Advances and Open Problems in Federated Learning

In recent years, deep neural networks have been successful in both industry and academia, especially for computer vision tasks. The great success of deep learning is mainly due to its scalability to encode large-scale data and to maneuver billions of model parameters. However, it is a challenge to deploy these cumbersome deep models on devices with limited resources, e.g., mobile phones and embedded devices, not only because of the high computational complexity but also the large storage requirements. To this end, a variety of model compression and acceleration techniques have been developed. As a representative type of model compression and acceleration, knowledge distillation effectively learns a small student model from a large teacher model. It has received rapid increasing attention from the community. This paper provides a comprehensive survey of knowledge distillation from the perspectives of knowledge categories, training schemes, teacher-student architecture, distillation algorithms, performance comparison and applications. Furthermore, challenges in knowledge distillation are briefly reviewed and comments on future research are discussed and forwarded.

Knowledge Distillation: A Survey

我的台灣, 看見心靈的故鄉 =2009林磐聳藝術與設計展

In the stochastic population protocol model, we are given a connected graph with n nodes, and in every time step, a scheduler samples an edge of the graph uniformly at random and the nodes connected by this edge interact. A fundamental task in this model is stable leader election, in which all nodes start in an identical state and the aim is to reach a configuration in which (1) exactly one node is elected as leader and (2) this node remains as the unique leader no matter what sequence of interactions follows. On cliques, the complexity of this problem has recently been settled: time-optimal protocols stabilize in Θ(n log n) expected steps using Θ(log log n) states, whereas protocols that use O(1) states require Θ(n2) expected steps. In this work, we investigate the complexity of stable leader election on general graphs. We provide the first non-trivial time lower bounds for leader election on general graphs, showing that, when moving beyond cliques, the complexity landscape of leader election becomes very diverse: the time required to elect a leader can range from O(1) to Θ(n3) expected steps. On the upper bound side, we first observe that there exists a protocol that is time-optimal on many graph families, but uses polynomially-many states. In contrast, we give a near-time-optimal protocol that uses only O(log2n) states that is at most a factor log n slower. Finally, we show that the constant-state protocol of Beauquier et al. [OPODIS 2013] is at most a factor n log n slower than the fast polynomial-state protocol. Moreover, among constant-state protocols, this protocol has near-optimal average case complexity on dense random graphs.

Near-Optimal Leader Election in Population Protocols on Graphs

Concurrent programming can be notoriously complex and error-prone. Programming bugs can arise from a variety of sources, such as operation re-reordering, or incomplete understanding of the memory model. A variety of formal and model checking methods have been developed to address this fundamental difficulty. While technically interesting, existing academic methods are still hard to apply to the large codebases typical of industrial deployments, which limits their practical impact.

Testing concurrency on the JVM with lincheck

We investigate fast and communication-efficient algorithms for the classic problem of minimizing a sum of strongly convex and smooth functions that are distributed among $n$ different nodes, which can communicate using a limited number of bits. Most previous communication-efficient approaches for this problem are limited to first-order optimization, and therefore have \emph{linear} dependence on the condition number in their communication complexity. We show that this dependence is not inherent: communication-efficient methods can in fact have sublinear dependence on the condition number. For this, we design and analyze the first communication-efficient distributed variants of preconditioned gradient descent for Generalized Linear Models, and for Newton's method. Our results rely on a new technique for quantizing both the preconditioner and the descent direction at each step of the algorithms, while controlling their convergence rate. We also validate our findings experimentally, showing fast convergence and reduced communication.

/pdf/communication-efficient-distributed-optimization-with-4yar5aycnv.pdf

Communication-Efficient Distributed Optimization with Quantized Preconditioners

We consider the problem of distributed variance reduction: $n$ machines each receive probabilistic estimates of an unknown true vector $\Delta$, and must cooperate to find a common estimate of $\Delta$ with lower variance, while minimizing communication. Variance reduction is closely related to the well-studied problem of distributed mean estimation, and is a key procedure in instances of distributed optimization, such as data-parallel stochastic gradient descent. Previous work typically assumes an upper bound on the norm of the input vectors, and achieves an output variance bound in terms of this norm. However, in real applications, the input vectors can be concentrated around the true vector $\Delta$, but $\Delta$ itself may have large norm. In this case, output variance bounds in terms of input norm perform poorly, and may even increase variance. In this paper, we show that output variance need not depend on input norm. We provide a method of quantization which allows variance reduction to be performed with solution quality dependent only on input variance, not on input norm, and show an analogous result for mean estimation. This method is effective over a wide range of communication regimes, from sublinear to superlinear in the dimension. We also provide lower bounds showing that in many cases the communication to output variance trade-off is asymptotically optimal. Further, we show experimentally that our method yields improvements for common optimization tasks, when compared to prior approaches to distributed mean estimation.

Distributed Mean Estimation with Optimal Error Bounds.

One of the key trends in computing over the past two decades has been increased distribution, both at the processor level, where multi-core architectures are now the norm, and at the system level, where many key services are currently distributed overmultiple machines. Thus, understanding the power and limitations of computing in a concurrent, distributed setting is one of the major challenges in Computer Science. In this thesis, we analyze the complexity of implementing concurrent data structures in asynchronous shared memory systems. We focus on the complexity of a classic distributed coordination task called renaming, in which a set of processes need to pick distinct names from a small set of identifiers. We present the first tight bounds for the time complexity of this problem, both for deterministic and randomized implementations, solving a long-standing open problem in the field. For deterministic algorithms, we prove a tight linear lower bound; for randomized solutions, we provide logarithmic upper and lower bounds on time complexity. Together, these results show an exponential separation between deterministic and randomized renaming solutions. Importantly, the lower bounds extend to implementations of practical shared-memory data structures, such as queues, stacks, and counters. From a technical perspective, this thesis highlights new connections between the distributed renaming problem and other fundamental objects, such as sorting networks, mutual exclusion, and counters. In particular, we show that sorting networks can be used to obtain optimal randomized solutions to renaming, and that, in turn, the existence of these solutions implies a linear lower bound on the complexity of the problem. In sum, the results in this thesis suggest that deterministic implementations of shared-memory data structures do not scale well in terms of worst-case time complexity. On the positive side, we emphasize randomization as a natural alternative, which can circumvent the deterministic lower bounds with high probability. Thus, a promising direction for future work is to extend our randomized renaming techniques to obtain efficient implementations of concurrent data structures.

Dan Alistarh

Papers

Near-Optimal Leader Election in Population Protocols on Graphs

Testing concurrency on the JVM with lincheck

Communication-Efficient Distributed Optimization with Quantized Preconditioners

Distributed Mean Estimation with Optimal Error Bounds.

Randomized versus Deterministic Implementations of Concurrent Data Structures