Apple Intelligence Foundation Language Models

We present foundation language models developed to power Apple Intelligence features, including a ~3 billion parameter model designed to run efficiently on devices and a large server-based language model designed for Private Cloud Compute. These models are designed to perform a wide range of tasks efficiently, accurately, and responsibly. This report describes the model architecture, the data used to train the model, the training process, how the models are optimized for inference, and the evaluation results. We highlight our focus on Responsible AI and how the principles are applied throughout the model development.

Mini-Batch Gradient-Based MCMC for Decentralized Massive MIMO Detection

Massive multiple-input multiple-output (MIMO) technology has significantly enhanced spectral and power efficiency in cellular communications and is expected to further evolve towards extra-large-scale MIMO. However, centralized processing for massive MIMO faces practical obstacles, including excessive computational complexity and a substantial volume of baseband data to be exchanged. To address these challenges, decentralized baseband processing has emerged as a promising solution. This approach involves partitioning the antenna array into clusters with dedicated computing hardware for parallel processing. In this paper, we investigate the gradient-based Markov chain Monte Carlo (MCMC) method -- an advanced MIMO detection technique known for its near-optimal performance in centralized implementation -- within the context of a decentralized baseband processing architecture. This decentralized design mitigates the computation burden at a single processing unit by utilizing computational resources in a distributed and parallel manner. Additionally, we integrate the mini-batch stochastic gradient descent method into the proposed decentralized detector, achieving remarkable performance with high efficiency. Simulation results demonstrate substantial performance gains of the proposed method over existing decentralized detectors across various scenarios. Moreover, complexity analysis reveals the advantages of the proposed decentralized strategy in terms of computation delay and interconnection bandwidth when compared to conventional centralized detectors.

Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Losses

We revisit the problem of federated learning (FL) with private data from people who do not trust the server or other silos/clients. In this context, every silo (e.g. hospital) has data from several people (e.g. patients) and needs to protect the privacy of each person's data (e.g. health records), even if the server and/or other silos try to uncover this data. Inter-Silo Record-Level Differential Privacy (ISRL-DP) prevents each silo's data from being leaked, by requiring that silo i's communications satisfy item-level differential privacy. Prior work arXiv:2203.06735 characterized the optimal excess risk bounds for ISRL-DP algorithms with homogeneous (i.i.d.) silo data and convex loss functions. However, two important questions were left open: (1) Can the same excess risk bounds be achieved with heterogeneous (non-i.i.d.) silo data? (2) Can the optimal risk bounds be achieved with fewer communication rounds? In this paper, we give positive answers to both questions. We provide novel ISRL-DP FL algorithms that achieve the optimal excess risk bounds in the presence of heterogeneous silo data. Moreover, our algorithms are more communication-efficient than the prior state-of-the-art. For smooth loss functions, our algorithm achieves the optimal excess risk bound and has communication complexity that matches the non-private lower bound. Additionally, our algorithms are more computationally efficient than the previous state-of-the-art.

Near-Optimal MIMO Detection Using Gradient-Based MCMC in Discrete Spaces

The discrete nature of transmitted symbols poses challenges for achieving optimal detection in multiple-input multiple-output (MIMO) systems associated with a large number of antennas. Recently, the combination of two powerful machine learning methods, Markov chain Monte Carlo (MCMC) sampling and gradient descent, has emerged as a highly efficient solution to address this issue. However, existing gradient-based MCMC detectors are heuristically designed and thus are theoretically untenable. To bridge this gap, we introduce a novel sampling algorithm tailored for discrete spaces. This algorithm leverages gradients from the underlying continuous spaces for acceleration while maintaining the validity of probabilistic sampling. We prove the convergence of this method and also analyze its convergence rate using both MCMC theory and empirical diagnostics. On this basis, we develop a MIMO detector that precisely samples from the target discrete distribution and generates posterior Bayesian estimates using these samples, whose performance is thereby theoretically guaranteed. Furthermore, our proposed detector is highly parallelizable and scalable to large MIMO dimensions, positioning it as a compelling candidate for next-generation wireless networks. Simulation results show that our detector achieves near-optimal performance, significantly outperforms state-of-the-art baselines, and showcases resilience to various system setups.

Large Scale Hierarchical Industrial Demand Time-Series Forecasting incorporating Sparsity

Hierarchical time-series forecasting (HTSF) is an important problem for many real-world business applications where the goal is to simultaneously forecast multiple time-series that are related to each other via a hierarchical relation. Recent works, however, do not address two important challenges that are typically observed in many demand forecasting applications at large companies. First, many time-series at lower levels of the hierarchy have high sparsity i.e., they have a significant number of zeros. Most HTSF methods do not address this varying sparsity across the hierarchy. Further, they do not scale well to the large size of the real-world hierarchy typically unseen in benchmarks used in literature. We resolve both these challenges by proposing HAILS, a novel probabilistic hierarchical model that enables accurate and calibrated probabilistic forecasts across the hierarchy by adaptively modeling sparse and dense time-series with different distributional assumptions and reconciling them to adhere to hierarchical constraints. We show the scalability and effectiveness of our methods by evaluating them against real-world demand forecasting datasets. We deploy HAILS at a large chemical manufacturing company for a product demand forecasting application with over ten thousand products and observe a significant 8.5\% improvement in forecast accuracy and 23% better improvement for sparse time-series. The enhanced accuracy and scalability make HAILS a valuable tool for improved business planning and customer experience.

Improved Implicit Neural Representation with Fourier Bases Reparameterized Training

Implicit Neural Representation (INR) as a mighty representation paradigm has achieved success in various computer vision tasks recently. Due to the low-frequency bias issue of vanilla multi-layer perceptron (MLP), existing methods have investigated advanced techniques, such as positional encoding and periodic activation function, to improve the accuracy of INR. In this paper, we connect the network training bias with the reparameterization technique and theoretically prove that weight reparameterization could provide us a chance to alleviate the spectral bias of MLP. Based on our theoretical analysis, we propose a Fourier reparameterization method which learns coefficient matrix of fixed Fourier bases to compose the weights of MLP. We evaluate the proposed Fourier reparameterization method on different INR tasks with various MLP architectures, including vanilla MLP, MLP with positional encoding and MLP with advanced activation function, etc. The superiority approximation results on different MLP architectures clearly validate the advantage of our proposed method. Armed with our Fourier reparameterization method, better INR with more textures and less artifacts can be learned from the training data.

Design of UAV flight state recognition and trajectory prediction system based on trajectory feature construction

With the impact of artificial intelligence on the traditional UAV industry, autonomous UAV flight has become a current hot research field. Based on the demand for research on critical technologies for autonomous flying UAVs, this paper addresses the field of flight state recognition and trajectory prediction of UAVs. This paper proposes a method to improve the accuracy of UAV trajectory prediction based on UAV flight state recognition and verifies it using two prediction models. Firstly, UAV flight data acquisition and data preprocessing are carried out; secondly, UAV flight trajectory features are extracted based on data fusion and a UAV flight state recognition model based on PCA-DAGSVM model is established; finally, two UAV flight trajectory prediction models are established and the trajectory prediction errors of the two prediction models are compared and analyzed after flight state recognition. The results show that: 1) the UAV flight state recognition model based on PCA-DAGSVM has good recognition effect. 2) compared with the traditional UAV trajectory prediction model, the prediction model based on flight state recognition can effectively reduce the prediction error.

Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary

Single Image Super-Resolution is a classic computer vision problem that involves estimating high-resolution (HR) images from low-resolution (LR) ones. Although deep neural networks (DNNs), especially Transformers for super-resolution, have seen significant advancements in recent years, challenges still remain, particularly in limited receptive field caused by window-based self-attention. To address these issues, we introduce a group of auxiliary Adaptive Token Dictionary to SR Transformer and establish an ATD-SR method. The introduced token dictionary could learn prior information from training data and adapt the learned prior to specific testing image through an adaptive refinement step. The refinement strategy could not only provide global information to all input tokens but also group image tokens into categories. Based on category partitions, we further propose a category-based self-attention mechanism designed to leverage distant but similar tokens for enhancing input features. The experimental results show that our method achieves the best performance on various single image super-resolution benchmarks.

Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention

Recently, Vision Transformer has achieved great success in recovering missing details in low-resolution sequences, i.e., the video super-resolution (VSR) task. Despite its superiority in VSR accuracy, the heavy computational burden as well as the large memory footprint hinder the deployment of Transformer-based VSR models on constrained devices. In this paper, we address the above issue by proposing a novel feature-level masked processing framework: VSR with Masked Intra and inter frame Attention (MIA-VSR). The core of MIA-VSR is leveraging feature-level temporal continuity between adjacent frames to reduce redundant computations and make more rational use of previously enhanced SR features. Concretely, we propose an intra-frame and inter-frame attention block which takes the respective roles of past features and input features into consideration and only exploits previously enhanced features to provide supplementary information. In addition, an adaptive block-wise mask prediction module is developed to skip unimportant computations according to feature similarity between adjacent frames. We conduct detailed ablation studies to validate our contributions and compare the proposed method with recent state-of-the-art VSR approaches. The experimental results demonstrate that MIA-VSR improves the memory and computation efficiency over state-of-the-art methods, without trading off PSNR accuracy. The code is available at https://github.com/LabShuHangGU/MIA-VSR.

Differentially Private Reward Estimation with Preference Feedback

Learning from preference-based feedback has recently gained considerable traction as a promising approach to align generative models with human interests. Instead of relying on numerical rewards, the generative models are trained using reinforcement learning with human feedback (RLHF). These approaches first solicit feedback from human labelers typically in the form of pairwise comparisons between two possible actions, then estimate a reward model using these comparisons, and finally employ a policy based on the estimated reward model. An adversarial attack in any step of the above pipeline might reveal private and sensitive information of human labelers. In this work, we adopt the notion of label differential privacy (DP) and focus on the problem of reward estimation from preference-based feedback while protecting privacy of each individual labelers. Specifically, we consider the parametric Bradley-Terry-Luce (BTL) model for such pairwise comparison feedback involving a latent reward parameter $\theta^* \in \mathbb{R}^d$. Within a standard minimax estimation framework, we provide tight upper and lower bounds on the error in estimating $\theta^*$ under both local and central models of DP. We show, for a given privacy budget $\epsilon$ and number of samples $n$, that the additional cost to ensure label-DP under local model is $\Theta \big(\frac{1}{ e^\epsilon-1}\sqrt{\frac{d}{n}}\big)$, while it is $\Theta\big(\frac{\text{poly}(d)}{\epsilon n} \big)$ under the weaker central model. We perform simulations on synthetic data that corroborate these theoretical results.