Causal Bayesian Networks provide an important tool for reasoning under uncertainty with potential application to many complex causal systems. Structure learning algorithms that can tell us something about the causal structure of these systems are becoming increasingly important. In the literature, the validity of these algorithms is often tested for sensitivity over varying sample sizes, hyper-parameters, and occasionally objective functions. In this paper, we show that the order in which the variables are read from data can have much greater impact on the accuracy of the algorithm than these factors. Because the variable ordering is arbitrary, any significant effect it has on learnt graph accuracy is concerning, and this raises questions about the validity of the results produced by algorithms that are sensitive to, but have not been assessed against, different variable orderings.
相關內容
Decentralized bilevel optimization has been actively studied in the past few years since it has widespread applications in machine learning. However, existing algorithms suffer from large communication complexity caused by the estimation of stochastic hypergradient, limiting their application to real-world tasks. To address this issue, we develop a novel decentralized stochastic bilevel gradient descent algorithm under the heterogeneous setting, which enjoys a small communication cost in each round and a small number of communication rounds. As such, it can achieve a much better communication complexity than existing algorithms without any strong assumptions regarding heterogeneity. To the best of our knowledge, this is the first stochastic algorithm achieving these theoretical results under the heterogeneous setting. At last, the experimental results confirm the efficacy of our algorithm.
State Machine Replication (SMR) protocols form the backbone of many distributed systems. Enterprises and startups increasingly build their distributed systems on the cloud due to its many advantages, such as scalability and cost-effectiveness. One of the first technical questions companies face when building a system on the cloud is which programming language to use. Among many factors that go into this decision is whether to use a language with garbage collection (GC), such as Java or Go, or a language with manual memory management, such as C++ or Rust. Today, companies predominantly prefer languages with GC, like Go, Kotlin, or even Python, due to ease of development; however, there is no free lunch: GC costs resources (memory and CPU) and performance (long tail latencies due to GC pauses). While there have been anecdotal reports of reduced cloud cost and improved tail latencies when switching from a language with GC to a language with manual memory management, so far, there has not been a systematic study of the GC overhead of running an SMR-based cloud system. This paper studies the overhead of running an SMR-based cloud system written in a language with GC. To this end, we design from scratch a canonical SMR system -- a MultiPaxos-based replicated in-memory key-value store -- and we implement it in C++, Java, Rust, and Go. We compare the performance and resource usage of these implementations when running on the cloud under different workloads and resource constraints and report our results. Our findings have implications for the design of cloud systems.
Recent innovations from machine learning allow for data unfolding, without binning and including correlations across many dimensions. We describe a set of known, upgraded, and new methods for ML-based unfolding. The performance of these approaches are evaluated on the same two datasets. We find that all techniques are capable of accurately reproducing the particle-level spectra across complex observables. Given that these approaches are conceptually diverse, they offer an exciting toolkit for a new class of measurements that can probe the Standard Model with an unprecedented level of detail and may enable sensitivity to new phenomena.
We investigate the learning of implicit neural representation (INR) using an overparameterized multilayer perceptron (MLP) via a novel nonparametric teaching perspective. The latter offers an efficient example selection framework for teaching nonparametrically defined (viz. non-closed-form) target functions, such as image functions defined by 2D grids of pixels. To address the costly training of INRs, we propose a paradigm called Implicit Neural Teaching (INT) that treats INR learning as a nonparametric teaching problem, where the given signal being fitted serves as the target function. The teacher then selects signal fragments for iterative training of the MLP to achieve fast convergence. By establishing a connection between MLP evolution through parameter-based gradient descent and that of function evolution through functional gradient descent in nonparametric teaching, we show for the first time that teaching an overparameterized MLP is consistent with teaching a nonparametric learner. This new discovery readily permits a convenient drop-in of nonparametric teaching algorithms to broadly enhance INR training efficiency, demonstrating 30%+ training time savings across various input modalities.
The Rust programming language restricts aliasing and mutability to provide static safety guarantees, which developers rely on to write secure and performant applications. However, Rust is frequently used to interoperate with other languages that have far weaker restrictions. These languages support cyclic and self-referential design patterns that conflict with current models of Rust's operational semantics, representing a potentially significant source of undefined behavior that no current tools can detect. We created MiriLLI, a tool which uses existing Rust and LLVM interpreters to jointly execute multi-language Rust applications. We used our tool in a large-scale study of Rust libraries that call foreign functions, and we found 45 instances of undefined or undesirable behavior. These include four bugs from libraries that had over 10,000 daily downloads on average, one from a component of the GNU Compiler Collection (GCC), and one from a library maintained by the Rust Project. Most of these errors were caused by incompatible aliasing and initialization patterns, incorrect foreign function bindings, and invalid type conversion. The majority of aliasing violations were caused by unsound operations in Rust, but they occurred in foreign code. The Rust community must invest in new tools for validating multi-language programs to ensure that developers can easily detect and fix these errors.
As machine learning models are increasingly deployed in dynamic environments, it becomes paramount to assess and quantify uncertainties associated with distribution shifts. A distribution shift occurs when the underlying data-generating process changes, leading to a deviation in the model's performance. The prediction interval, which captures the range of likely outcomes for a given prediction, serves as a crucial tool for characterizing uncertainties induced by their underlying distribution. In this paper, we propose methodologies for aggregating prediction intervals to obtain one with minimal width and adequate coverage on the target domain under unsupervised domain shift, under which we have labeled samples from a related source domain and unlabeled covariates from the target domain. Our analysis encompasses scenarios where the source and the target domain are related via i) a bounded density ratio, and ii) a measure-preserving transformation. Our proposed methodologies are computationally efficient and easy to implement. Beyond illustrating the performance of our method through a real-world dataset, we also delve into the theoretical details. This includes establishing rigorous theoretical guarantees, coupled with finite sample bounds, regarding the coverage and width of our prediction intervals. Our approach excels in practical applications and is underpinned by a solid theoretical framework, ensuring its reliability and effectiveness across diverse contexts.
In this paper, we deeply explore several mechanisms employed by Transformer-based language models in factual recall tasks. In zero-shot scenarios, given a prompt like ``The capital of France is,'' task-specific attention heads extract the topic entity, such as ``France,'' from the context and pass it to subsequent MLPs to recall the required answer such as ``Paris.'' We introduce a novel analysis method aimed at decomposing the outputs of the MLP into components understandable by humans. Through this method, we quantify the function of the MLP layer following these task-specific heads. In the residual stream, it either erases or amplifies the information originating from individual heads. Moreover, it generates a component that redirects the residual stream towards the direction of its expected answer. These zero-shot mechanisms are also employed in few-shot scenarios. Additionally, we observed a widely existent anti-overconfidence mechanism in the final layer of models, which suppresses correct predictions. We mitigate this suppression by leveraging our interpretation to improve factual recall confidence. Our interpretations have been evaluated across various language models, including the GPT-2 families, 1.3B OPT, and 7B Llama-2, encompassing diverse tasks spanning various domains of factual knowledge.
Since the introduction of the Kolmogorov complexity of binary sequences in the 1960s, there have been significant advancements in the topic of complexity measures for randomness assessment, which are of fundamental importance in theoretical computer science and of practical interest in cryptography. This survey reviews notable research from the past four decades on the linear, quadratic and maximum-order complexities of pseudo-random sequences and their relations with Lempel-Ziv complexity, expansion complexity, 2-adic complexity, and correlation measures.
Massively multilingual neural machine translation (MMNMT) has been proven to enhance the translation quality of low-resource languages. In this paper, we empirically investigate the translation robustness of Indonesian-Chinese translation in the face of various naturally occurring noise. To assess this, we create a robustness evaluation benchmark dataset for Indonesian-Chinese translation. This dataset is automatically translated into Chinese using four NLLB-200 models of different sizes. We conduct both automatic and human evaluations. Our in-depth analysis reveal the correlations between translation error types and the types of noise present, how these correlations change across different model sizes, and the relationships between automatic evaluation indicators and human evaluation indicators. The dataset is publicly available at //github.com/tjunlp-lab/ID-ZH-MTRobustEval.
Large language models (LLMs) are now being used in a wide variety of contexts, including as creativity support tools (CSTs) intended to help their users come up with new ideas. But do LLMs actually support user creativity? We hypothesized that the use of an LLM as a CST might make the LLM's users feel more creative, and even broaden the range of ideas suggested by each individual user, but also homogenize the ideas suggested by different users. We conducted a 36-participant comparative user study and found, in accordance with the homogenization hypothesis, that different users tended to produce less semantically distinct ideas with ChatGPT than with an alternative CST. Additionally, ChatGPT users generated a greater number of more detailed ideas, but felt less responsible for the ideas they generated. We discuss potential implications of these findings for users, designers, and developers of LLM-based CSTs.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191