Large language models are typically aligned with human preferences by optimizing $\textit{reward models}$ (RMs) fitted to human feedback. However, human preferences are multi-faceted, and it is increasingly common to derive reward from a composition of simpler reward models which each capture a different aspect of language quality. This itself presents a challenge, as it is difficult to appropriately weight these component RMs when combining them. Compounding this difficulty, because any RM is only a proxy for human evaluation, this process is vulnerable to $\textit{overoptimization}$, wherein past a certain point, accumulating higher reward is associated with worse human ratings. In this paper, we perform, to our knowledge, the first study on overoptimization in composite RMs, showing that correlation between component RMs has a significant effect on the locations of these points. We then introduce an approach to solve this issue using constrained reinforcement learning as a means of preventing the agent from exceeding each RM's threshold of usefulness. Our method addresses the problem of weighting component RMs by learning dynamic weights, naturally expressed by Lagrange multipliers. As a result, each RM stays within the range at which it is an effective proxy, improving evaluation performance. Finally, we introduce an adaptive method using gradient-free optimization to identify and optimize towards these points during a single run.

While large language models (LLMs) have shown impressive results for more objective tasks such as QA and retrieval, it remains nontrivial to evaluate their performance on open-ended text generation for reasons including (1) data contamination; (2) multi-dimensional evaluation criteria; and (3) subjectiveness stemming from reviewers' personal preferences. To address such issues, we propose to model personalization in an uncontaminated open-ended generation assessment. We create two new datasets Per-MPST and Per-DOC for personalized story evaluation, by re-purposing existing datasets with proper anonymization and new personalized labels. SE to infer reviewer preferences and provide a personalized evaluation. SE predicts either a detailed review or fine-grained comparison in several aspects (such as interestingness and surprise) for that reviewer on a new text input. SE outperforms GPT-4 by 15.8% on Kendall correlation of story ratings, and by 13.7% on pairwise preference prediction accuracy. Both datasets and code will be released. LLMs' abilities in open-ended text generation are still insufficiently Meanwhile, some recent metrics propose to directly use strong LLMs as evaluators (Fu et al., 2023; Liu et al., Besides, the contamination problem may affect the evaluation performance, similar to other tasks (Chang et al., 2023). Human evaluation is also widely used in open-ended text generation. However, it may be timeconsuming and expensive, especially for larger-scale evaluation. This personalization issue in text generation has recently attracted increasing attention (Flek, 2020; Dudy et al., 2021), but personalization in evaluation is still under-explored. In this paper, we explore personalized evaluation for long-form story generation, where the assessment is heavily influenced by reviewers' personal preferences. For example, Figure 1 illustrates two reviewers' opinions when comparing two plots derived from the same premise. Reviewer 1 prefers Plot A for its uplifting ending while Reviewer 2 favors Plot B because of the plot complexity and empathetic ending. To model such diverse preferences in story evaluation, the major difficulty lies in the following aspects: personalization story evaluation dataset modeling, i.e., uncontaminated story datasets with personal information, and reviewer preference modeling, i.e., effective methods to capture reviewer preferences and evaluate stories from a particular individual's perspective. Few story evaluation datasets have personal labels due to the difficulty of collecting personal information. Besides, most existing story datasets have been exposed to LLMs.

Photoplethysmogram (PPG) signals are easily contaminated by motion artifacts in real-world settings, despite their widespread use in Internet-of-Things (IoT) based wearable and smart health devices for cardiovascular health monitoring. This study proposed a lightweight deep neural network, called Tiny-PPG, for accurate and real-time PPG artifact segmentation on IoT edge devices. The model was trained and tested on a public dataset, PPG DaLiA, which featured complex artifacts with diverse lengths and morphologies during various daily activities of 15 subjects using a watch-type device (Empatica E4). The model structure, training method and loss function were specifically designed to balance detection accuracy and speed for real-time PPG artifact detection in resource-constrained embedded devices. To optimize the model size and capability in multi-scale feature representation, the model employed depth-wise separable convolution and atrous spatial pyramid pooling modules, respectively. Additionally, the contrastive loss was also utilized to further optimize the feature embeddings. With additional model pruning, Tiny-PPG achieved state-of-the-art detection accuracy of 87.4% while only having 19,726 model parameters (0.15 megabytes), and was successfully deployed on an STM32 embedded system for real-time PPG artifact detection. Therefore, this study provides an effective solution for resource-constraint IoT smart health devices in PPG artifact detection.

In the field of semi-supervised medical image segmentation, the shortage of labeled data is the fundamental problem. How to effectively learn image features from unlabeled images to improve segmentation accuracy is the main research direction in this field. Traditional self-training methods can partially solve the problem of insufficient labeled data by generating pseudo labels for iterative training. However, noise generated due to the model's uncertainty during training directly affects the segmentation results. Therefore, we added sample-level and pixel-level uncertainty to stabilize the training process based on the self-training framework. Specifically, we saved several moments of the model during pre-training, and used the difference between their predictions on unlabeled samples as the sample-level uncertainty estimate for that sample. Then, we gradually add unlabeled samples from easy to hard during training. At the same time, we added a decoder with different upsampling methods to the segmentation network and used the difference between the outputs of the two decoders as pixel-level uncertainty. In short, we selectively retrained unlabeled samples and assigned pixel-level uncertainty to pseudo labels to optimize the self-training process. We compared the segmentation results of our model with five semi-supervised approaches on the public 2017 ACDC dataset and 2018 Prostate dataset. Our proposed method achieves better segmentation performance on both datasets under the same settings, demonstrating its effectiveness, robustness, and potential transferability to other medical image segmentation tasks. Keywords: Medical image segmentation, semi-supervised learning, self-training, uncertainty estimation

As the scale of the datasets and parameterized models used to perform computation over data continues to grow [43, 53], distributing workloads across multiple devices becomes essential for enabling progress. The choice of architecture for large-scale training and inference must not only make the best use of computational and memory resources, but also contend with the fact that communication may become a bottleneck [85]. When using modern optical interconnects, classical computers exchange bits represented by light. This however does not fully utilize the potential of the physical substrate; given suitable computational capabilities and algorithms, the quantum nature of light can be harnessed as a powerful communication resource. Here we show that for a broad class of parameterized models, if quantum bits (qubits) are communicated instead of classical bits, an exponential reduction in the communication required to perform inference and gradientbased training can be achieved. This protocol additionally guarantees improved privacy of both the user data and model parameters through natural features of quantum mechanics, without the need for additional cryptographic or privacy protocols. To our knowledge, this is the first example of generic, exponential quantum advantage on problems that occur naturally in the training and deployment of large machine learning models. These types of communication advantages help scope the future roles and interplay between quantum and classical communication for distributed machine learning.

Introduction: The amount of data generated by original research is growing exponentially. Publicly releasing them is recommended to comply with the Open Science principles. However, data collected from human participants cannot be released as-is without raising privacy concerns. Fully synthetic data represent a promising answer to this challenge. This approach is explored by the French Centre de Recherche en {\'E}pid{\'e}miologie et Sant{\'e} des Populations in the form of a synthetic data generation framework based on Classification and Regression Trees and an original distance-based filtering. The goal of this work was to develop a refined version of this framework and to assess its risk-utility profile with empirical and formal tools, including novel ones developed for the purpose of this evaluation.Materials and Methods: Our synthesis framework consists of four successive steps, each of which is designed to prevent specific risks of disclosure. We assessed its performance by applying two or more of these steps to a rich epidemiological dataset. Privacy and utility metrics were computed for each of the resulting synthetic datasets, which were further assessed using machine learning approaches.Results: Computed metrics showed a satisfactory level of protection against attribute disclosure attacks for each synthetic dataset, especially when the full framework was used. Membership disclosure attacks were formally prevented without significantly altering the data. Machine learning approaches showed a low risk of success for simulated singling out and linkability attacks. Distributional and inferential similarity with the original data were high with all datasets.Discussion: This work showed the technical feasibility of generating publicly releasable synthetic data using a multi-step framework. Formal and empirical tools specifically developed for this demonstration are a valuable contribution to this field. Further research should focus on the extension and validation of these tools, in an effort to specify the intrinsic qualities of alternative data synthesis methods.Conclusion: By successfully assessing the quality of data produced using a novel multi-step synthetic data generation framework, we showed the technical and conceptual soundness of the Open-CESP initiative, which seems ripe for full-scale implementation.

Senior fellow at the Gatestone Institute Gordon Chang joined'Cavuto Live' to discuss the U.S.'s relationship with China amid the highly anticipated G20 Summit. Emerging technologies like artificial intelligence (AI) should be used as "tools of opportunity, not as weapons of oppression," President Biden remarked recently. But this exhortation makes his subsequent vow to work directly with "our competitors" to harness the power of AI "for good" all the more curious. Working with our competitors, like China, would only empower the Chinese Communist Party (CCP) to write the rules of the road for AI. And we don't want China in the driver's seat.

We present a novel unsupervised machine-learning sock sensor based on Gaussian Mixture Models (GMMs). The proposed GMM sensor demonstrates remarkable accuracy in detecting shocks and is robust across diverse test cases with significantly less parameter tuning than other options. We compare the GMM-based sensor with state-of-the-art alternatives. All methods are integrated into a high-order compressible discontinuous Galerkin solver, where two stabilization approaches are coupled to the sensor to provide examples of possible applications. The Sedov blast and double Mach reflection cases demonstrate that our proposed sensor can enhance hybrid sub-cell flux-differencing formulations by providing accurate information of the nodes that require low-order blending. Besides, supersonic test cases including high Reynolds numbers showcase the sensor performance when used to introduce entropy-stable artificial viscosity to capture shocks, demonstrating the same effectiveness as fine-tuned state-of-the-art sensors. The adaptive nature and ability to function without extensive training datasets make this GMM-based sensor suitable for complex geometries and varied flow configurations. Our study reveals the potential of unsupervised machine-learning methods, exemplified by this GMM sensor, to improve the robustness and efficiency of advanced CFD codes.

Symbolic Regression is the study of algorithms that automate the search for analytic expressions that fit data. While recent advances in deep learning have generated renewed interest in such approaches, the development of symbolic regression methods has not been focused on physics, where we have important additional constraints due to the units associated with our data. Here we present $\Phi$-SO, a Physical Symbolic Optimization framework for recovering analytical symbolic expressions from physics data using deep reinforcement learning techniques by learning units constraints. Our system is built, from the ground up, to propose solutions where the physical units are consistent by construction. This is useful not only in eliminating physically impossible solutions, but because the "grammatical" rules of dimensional analysis restrict enormously the freedom of the equation generator, thus vastly improving performance. The algorithm can be used to fit noiseless data, which can be useful for instance when attempting to derive an analytical property of a physical model, and it can also be used to obtain analytical approximations to noisy data. We test our machinery on a standard benchmark of equations from the Feynman Lectures on Physics and other physics textbooks, achieving state-of-the-art performance in the presence of noise (exceeding 0.1%) and show that it is robust even in the presence of substantial (10%) noise. We showcase its abilities on a panel of examples from astrophysics.

While one-dimensional convolutional neural networks (1D-CNNs) have been empirically proven effective in time series classification tasks, we find that there remain undesirable outcomes that could arise in their application, motivating us to further investigate and understand their underlying mechanisms. In this work, we propose a Temporal Convolutional Explorer (TCE) to empirically explore the learning behavior of 1D-CNNs from the perspective of the frequency domain. Our TCE analysis highlights that deeper 1D-CNNs tend to distract the focus from the low-frequency components leading to the accuracy degradation phenomenon, and the disturbing convolution is the driving factor. Then, we leverage our findings to the practical application and propose a regulatory framework, which can easily be integrated into existing 1D-CNNs. It aims to rectify the suboptimal learning behavior by enabling the network to selectively bypass the specified disturbing convolutions. Finally, through comprehensive experiments on widely-used UCR, UEA, and UCI benchmarks, we demonstrate that 1) TCE's insight into 1D-CNN's learning behavior; 2) our regulatory framework enables state-of-the-art 1D-CNNs to get improved performances with less consumption of memory and computational overhead.