Recent work has shown that viewing allocators as black-box 2DBP solvers bears meaning. For instance, there exists a 2DBP-based fragmentation metric which often correlates monotonically with maximum resident set size (RSS). Given the field's indeterminacy with respect to fragmentation definitions, as well as the immense value of physical memory savings, we are motivated to set allocator-generated placements against their 2DBP-devised, makespan-optimizing counterparts. Of course, allocators must operate online while 2DBP algorithms work on complete request traces; but since both sides optimize criteria related to minimizing memory wastage, the idea of studying their relationship preserves its intellectual--and practical--interest. Unfortunately no implementations of 2DBP algorithms for DSA are available. This paper presents a first, though partial, implementation of the state-of-the-art. We validate its functionality by comparing its outputs' makespan to the theoretical upper bound provided by the original authors. Along the way, we identify and document key details to assist analogous future efforts. Our experiments comprise 4 modern allocators and 8 real application workloads. We make several notable observations on our empirical evidence: in terms of makespan, allocators outperform Robson's worst-case lower bound $93.75\%$ of the time. In $87.5\%$ of cases, GNU's \texttt{malloc} implementation demonstrates equivalent or superior performance to the 2DBP state-of-the-art, despite the second operating offline. Most surprisingly, the 2DBP algorithm proves competent in terms of fragmentation, producing up to $2.46$x better solutions. Future research can leverage such insights towards memory-targeting optimizations.
相關內容
Empirical evidence demonstrates that citations received by scholarly publications follow a pattern of preferential attachment, resulting in a power-law distribution. Such asymmetry has sparked significant debate regarding the use of citations for research evaluation. However, a consensus has yet to be established concerning the historical trends in citation concentration. Are citations becoming more concentrated in a small number of articles? Or have recent geopolitical and technical changes in science led to more decentralized distributions? This ongoing debate stems from a lack of technical clarity in measuring inequality. Given the variations in citation practices across disciplines and over time, it is crucial to account for multiple factors that can influence the findings. This article explores how reference-based and citation-based approaches, uncited articles, citation inflation, the expansion of bibliometric databases, disciplinary differences, and self-citations affect the evolution of citation concentration. Our results indicate a decreasing trend in citation concentration, primarily driven by a decline in uncited articles, which, in turn, can be attributed to the growing significance of Asia and Europe. On the whole, our findings clarify current debates on citation concentration and show that, contrary to a widely-held belief, citations are increasingly scattered.
We present a deep learning segmentation model that can automatically and robustly segment all major anatomical structures in body CT images. In this retrospective study, 1204 CT examinations (from the years 2012, 2016, and 2020) were used to segment 104 anatomical structures (27 organs, 59 bones, 10 muscles, 8 vessels) relevant for use cases such as organ volumetry, disease characterization, and surgical or radiotherapy planning. The CT images were randomly sampled from routine clinical studies and thus represent a real-world dataset (different ages, pathologies, scanners, body parts, sequences, and sites). The authors trained an nnU-Net segmentation algorithm on this dataset and calculated Dice similarity coefficients (Dice) to evaluate the model's performance. The trained algorithm was applied to a second dataset of 4004 whole-body CT examinations to investigate age dependent volume and attenuation changes. The proposed model showed a high Dice score (0.943) on the test set, which included a wide range of clinical data with major pathologies. The model significantly outperformed another publicly available segmentation model on a separate dataset (Dice score, 0.932 versus 0.871, respectively). The aging study demonstrated significant correlations between age and volume and mean attenuation for a variety of organ groups (e.g., age and aortic volume; age and mean attenuation of the autochthonous dorsal musculature). The developed model enables robust and accurate segmentation of 104 anatomical structures. The annotated dataset (//doi.org/10.5281/zenodo.6802613) and toolkit (//www.github.com/wasserth/TotalSegmentator) are publicly available.
Despite its success, Model Predictive Control (MPC) often requires intensive task-specific engineering and tuning. On the other hand, Reinforcement Learning (RL) architectures minimize this effort, but need extensive data collection and lack interpretability and safety. An open research question is how to combine the advantages of RL and MPC to exploit the best of both worlds. This paper introduces a novel modular RL architecture that bridges these two approaches. By placing a differentiable MPC in the heart of an actor-critic RL agent, the proposed system enables short-term predictions and optimization of actions based on system dynamics, while retaining the end-to-end training benefits and exploratory behavior of an RL agent. The proposed approach effectively handles two different time-horizon scales: short-term decisions managed by the actor MPC and long term ones managed by the critic network. This provides a promising direction for RL, which combines the advantages of model-based and end-to-end learning methods. We validate the approach in simulated and real-world experiments on a quadcopter platform performing different high-level tasks, and show that the proposed method can learn complex behaviours end-to-end while retaining the properties of an MPC.
Long-term engagement is preferred over immediate engagement in sequential recommendation as it directly affects product operational metrics such as daily active users (DAUs) and dwell time. Meanwhile, reinforcement learning (RL) is widely regarded as a promising framework for optimizing long-term engagement in sequential recommendation. However, due to expensive online interactions, it is very difficult for RL algorithms to perform state-action value estimation, exploration and feature extraction when optimizing long-term engagement. In this paper, we propose ResAct which seeks a policy that is close to, but better than, the online-serving policy. In this way, we can collect sufficient data near the learned policy so that state-action values can be properly estimated, and there is no need to perform online exploration. ResAct optimizes the policy by first reconstructing the online behaviors and then improving it via a Residual Actor. To extract long-term information, ResAct utilizes two information-theoretical regularizers to confirm the expressiveness and conciseness of features. We conduct experiments on a benchmark dataset and a large-scale industrial dataset which consists of tens of millions of recommendation requests. Experimental results show that our method significantly outperforms the state-of-the-art baselines in various long-term engagement optimization tasks.
Learning paradigms based purely on offline data as well as those based solely on sequential online learning have been well-studied in the literature. In this paper, we consider combining offline data with online learning, an area less studied but of obvious practical importance. We consider the stochastic $K$-armed bandit problem, where our goal is to identify the arm with the highest mean in the presence of relevant offline data, with confidence $1-\delta$. We conduct a lower bound analysis on policies that provide such $1-\delta$ probabilistic correctness guarantees. We develop algorithms that match the lower bound on sample complexity when $\delta$ is small. Our algorithms are computationally efficient with an average per-sample acquisition cost of $\tilde{O}(K)$, and rely on a careful characterization of the optimality conditions of the lower bound problem.
The bandits with knapsack (BwK) framework models online decision-making problems in which an agent makes a sequence of decisions subject to resource consumption constraints. The traditional model assumes that each action consumes a non-negative amount of resources and the process ends when the initial budgets are fully depleted. We study a natural generalization of the BwK framework which allows non-monotonic resource utilization, i.e., resources can be replenished by a positive amount. We propose a best-of-both-worlds primal-dual template that can handle any online learning problem with replenishment for which a suitable primal regret minimizer exists. In particular, we provide the first positive results for the case of adversarial inputs by showing that our framework guarantees a constant competitive ratio $\alpha$ when $B=\Omega(T)$ or when the possible per-round replenishment is a positive constant. Moreover, under a stochastic input model, our algorithm yields an instance-independent $\tilde{O}(T^{1/2})$ regret bound which complements existing instance-dependent bounds for the same setting. Finally, we provide applications of our framework to some economic problems of practical relevance.
Short Message Service (SMS) remains one of the most popular communication channels since its introduction in 2G cellular networks. In this paper, we demonstrate that merely receiving silent SMS messages regularly opens a stealthy side-channel that allows other regular network users to infer the whereabouts of the SMS recipient. The core idea is that receiving an SMS inevitably generates Delivery Reports whose reception bestows a timing attack vector at the sender. We conducted experiments across various countries, operators, and devices to show that an attacker can deduce the location of an SMS recipient by analyzing timing measurements from typical receiver locations. Our results show that, after training an ML model, the SMS sender can accurately determine multiple locations of the recipient. For example, our model achieves up to 96% accuracy for locations across different countries, and 86% for two locations within Belgium. Due to the way cellular networks are designed, it is difficult to prevent Delivery Reports from being returned to the originator making it challenging to thwart this covert attack without making fundamental changes to the network architecture.
As generative AI becomes more prevalent, it is important to study how human users interact with such models. In this work, we investigate how people use text-to-image models to generate desired target images. To study this interaction, we created ArtWhisperer, an online game where users are given a target image and are tasked with iteratively finding a prompt that creates a similar-looking image as the target. Through this game, we recorded over 50,000 human-AI interactions; each interaction corresponds to one text prompt created by a user and the corresponding generated image. The majority of these are repeated interactions where a user iterates to find the best prompt for their target image, making this a unique sequential dataset for studying human-AI collaborations. In an initial analysis of this dataset, we identify several characteristics of prompt interactions and user strategies. People submit diverse prompts and are able to discover a variety of text descriptions that generate similar images. Interestingly, prompt diversity does not decrease as users find better prompts. We further propose to a new metric the study the steerability of AI using our dataset. We define steerability as the expected number of interactions required to adequately complete a task. We estimate this value by fitting a Markov chain for each target task and calculating the expected time to reach an adequate score in the Markov chain. We quantify and compare AI steerability across different types of target images and two different models, finding that images of cities and natural world images are more steerable than artistic and fantasy images. These findings provide insights into human-AI interaction behavior, present a concrete method of assessing AI steerability, and demonstrate the general utility of the ArtWhisperer dataset.
This paper considers the Westervelt equation, one of the most widely used models in nonlinear acoustics, and seeks to recover two spatially-dependent parameters of physical importance from time-trace boundary measurements. Specifically, these are the nonlinearity parameter $\kappa(x)$ often referred to as $B/A$ in the acoustics literature and the wave speed $c_0(x)$. The determination of the spatial change in these quantities can be used as a means of imaging. We consider identifiability from one or two boundary measurements as relevant in these applications. For a reformulation of the problem in terms of the squared slowness $\mathfrak{s}=1/c_0^2$ and the combined coefficient $\eta=\frac{B/A+2}{\varrho_0 c_0^4}$ we devise a frozen Newton method and prove its convergence. The effectiveness (and limitations) of this iterative scheme are demonstrated by numerical examples.
Dynamic Interval Restrictions on Action Spaces in Deep Reinforcement Learning for Obstacle Avoidance
Deep reinforcement learning algorithms typically act on the same set of actions. However, this is not sufficient for a wide range of real-world applications where different subsets are available at each step. In this thesis, we consider the problem of interval restrictions as they occur in pathfinding with dynamic obstacles. When actions that lead to collisions are avoided, the continuous action space is split into variable parts. Recent research learns with strong assumptions on the number of intervals, is limited to convex subsets, and the available actions are learned from the observations. Therefore, we propose two approaches that are independent of the state of the environment by extending parameterized reinforcement learning and ConstraintNet to handle an arbitrary number of intervals. We demonstrate their performance in an obstacle avoidance task and compare the methods to penalties, projection, replacement, as well as discrete and continuous masking from the literature. The results suggest that discrete masking of action-values is the only effective method when constraints did not emerge during training. When restrictions are learned, the decision between projection, masking, and our ConstraintNet modification seems to depend on the task at hand. We compare the results with varying complexity and give directions for future work.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191