Thanks to their dependency structure, non-parametric Hidden Markov Models (HMMs) are able to handle model-based clustering without specifying group distributions. The aim of this work is to study the Bayes risk of clustering when using HMMs and to propose associated clustering procedures. We first give a result linking the Bayes risk of classification and the Bayes risk of clustering, which we use to identify the key quantity determining the difficulty of the clustering task. We also give a proof of this result in the i.i.d. framework, which might be of independent interest. Then we study the excess risk of the plugin classifier. All these results are shown to remain valid in the online setting where observations are clustered sequentially. Simulations illustrate our findings.

As more swatting incidents are reported, two former law enforcement officers warn about artificial intelligence's negative impact on combatting false threats. Artificial intelligence advancements have helped drive an increase in swatting calls, forcing police to dash to scenes prepared for the worst and endangering Americans' emotional health or even their lives, a 22-year FBI veteran told Fox News. "They're doing it to create chaos," said James Turgal, vice president of the information security company Optiv. "They're utilizing this technology, which emboldens them because it's so much harder for law enforcement to track that back." Swatting -- when someone makes a false 911 report to illicit a large and aggressive police response -- has become increasingly common over the last decade as it becomes easier for callers to mask their voices, phone numbers and IP addresses to remain anonymous.

Training robots with reinforcement learning (RL) typically involves heavy interactions with the environment, and the acquired skills are often sensitive to changes in task environments and robot kinematics. Transfer RL aims to leverage previous knowledge to accelerate learning of new tasks or new body configurations. However, existing methods struggle to generalize to novel robot-task combinations and scale to realistic tasks due to complex architecture design or strong regularization that limits the capacity of the learned policy. We propose Policy Stitching, a novel framework that facilitates robot transfer learning for novel combinations of robots and tasks. Our key idea is to apply modular policy design and align the latent representations between the modular interfaces. Our method allows direct stitching of the robot and task modules trained separately to form a new policy for fast adaptation. Our simulated and real-world experiments on various 3D manipulation tasks demonstrate the superior zero-shot and few-shot transfer learning performances of our method. Our project website is at: http://generalroboticslab.com/PolicyStitching/ .

The widespread adoption of large language models (LLMs) makes it important to recognize their strengths and limitations. We argue that in order to develop a holistic understanding of these systems we need to consider the problem that they were trained to solve: next-word prediction over Internet text. By recognizing the pressures that this task exerts we can make predictions about the strategies that LLMs will adopt, allowing us to reason about when they will succeed or fail. This approach - which we call the teleological approach - leads us to identify three factors that we hypothesize will influence LLM accuracy: the probability of the task to be performed, the probability of the target output, and the probability of the provided input. We predict that LLMs will achieve higher accuracy when these probabilities are high than when they are low - even in deterministic settings where probability should not matter. To test our predictions, we evaluate two LLMs (GPT-3.5 and GPT-4) on eleven tasks, and we find robust evidence that LLMs are influenced by probability in the ways that we have hypothesized. In many cases, the experiments reveal surprising failure modes. For instance, GPT-4's accuracy at decoding a simple cipher is 51% when the output is a high-probability word sequence but only 13% when it is low-probability. These results show that AI practitioners should be careful about using LLMs in low-probability situations. More broadly, we conclude that we should not evaluate LLMs as if they are humans but should instead treat them as a distinct type of system - one that has been shaped by its own particular set of pressures.

This paper presents a state-of-the-art solution to the LongEval CLEF 2023 Lab Task 2: LongEval-Classification. The goal of this task is to improve and preserve the performance of sentiment analysis models across shorter and longer time periods. Our framework feeds date-prefixed textual inputs to a pre-trained language model, where the timestamp is included in the text. We show date-prefixed samples better conditions model outputs on the temporal context of the respective texts. Moreover, we further boost performance by performing self-labeling on unlabeled data to train a student model. We augment the self-labeling process using a novel augmentation strategy leveraging the date-prefixed formatting of our samples. We demonstrate concrete performance gains on the LongEval-Classification evaluation set over non-augmented self-labeling. Our framework achieves a 2nd place ranking with an overall score of 0.6923 and reports the best Relative Performance Drop (RPD) of -0.0656 over the short evaluation set.

Memory performance is a bottleneck in graph analytics acceleration. Existing Machine Learning (ML) prefetchers struggle with phase transitions and irregular memory accesses in graph processing. We propose MPGraph, an ML-based Prefetcher for Graph analytics using domain specific models. MPGraph introduces three novel optimizations: soft detection for phase transitions, phase-specific multi-modality models for access delta and page predictions, and chain spatio-temporal prefetching (CSTP) for prefetch control. Our transition detector achieves 34.17-82.15% higher precision compared with Kolmogorov-Smirnov Windowing and decision tree. Our predictors achieve 6.80-16.02% higher F1-score for delta and 11.68-15.41% higher accuracy-at-10 for page prediction compared with LSTM and vanilla attention models. Using CSTP, MPGraph achieves 12.52-21.23% IPC improvement, outperforming state-of-the-art non-ML prefetcher BO by 7.58-12.03% and ML-based prefetchers Voyager and TransFetch by 3.27-4.58%. For practical implementation, we demonstrate MPGraph using compressed models with reduced latency shows significantly superior accuracy and coverage compared with BO, leading to 3.58% higher IPC improvement.

The quintessential learning algorithm of empirical risk minimization (ERM) is known to fail in various settings for which uniform convergence does not characterize learning. It is therefore unsurprising that the practice of machine learning is rife with considerably richer algorithmic techniques for successfully controlling model capacity. Nevertheless, no such technique or principle has broken away from the pack to characterize optimal learning in these more general settings. The purpose of this work is to characterize the role of regularization in perhaps the simplest setting for which ERM fails: multiclass learning with arbitrary label sets. Using one-inclusion graphs (OIGs), we exhibit optimal learning algorithms that dovetail with tried-and-true algorithmic principles: Occam's Razor as embodied by structural risk minimization (SRM), the principle of maximum entropy, and Bayesian reasoning. Most notably, we introduce an optimal learner which relaxes structural risk minimization on two dimensions: it allows the regularization function to be "local" to datapoints, and uses an unsupervised learning stage to learn this regularizer at the outset. We justify these relaxations by showing that they are necessary: removing either dimension fails to yield a near-optimal learner. We also extract from OIGs a combinatorial sequence we term the Hall complexity, which is the first to characterize a problem's transductive error rate exactly. Lastly, we introduce a generalization of OIGs and the transductive learning setting to the agnostic case, where we show that optimal orientations of Hamming graphs -- judged using nodes' outdegrees minus a system of node-dependent credits -- characterize optimal learners exactly. We demonstrate that an agnostic version of the Hall complexity again characterizes error rates exactly, and exhibit an optimal learner using maximum entropy programs.

In Proceedings of the IEEE Workshop on Exploring Opportunities and Challenges for Natural Language Techniques to Support Visual Analysis.

It takes a village: Supporting inquiry- and equity-oriented computer science pedagogy through a professional learning community.

In all the frenzied discourse about large language models (LLMs) such as GPT-4 there is one point on which everyone seems to agree: these models are essentially stochastic parrots – namely, machines that are good at generating convincing sentences, but do not actually understand the meaning of the language they are processing. They have somehow "read" (that is, ingested) everything ever published in machine-readable form and create sentences word by word, at each point making a statistical guess of "what one might expect someone to write after seeing what people have written on billions of webpages, etc". Ever since ChatGPT arrived last November, people have been astonished by the capabilities of these parrots – how humanlike they seem to be and so on. But consolation was drawn initially from the thought that since the models were drawing only on what already resided in their capacious memories, then they couldn't be genuinely original: they would just regurgitate the conventional wisdom embedded in their training data. That comforting thought didn't last long, though, as experimenters kept finding startling and unpredictable behaviours of LLMs – facets now labelled "emergent abilities".