Meta (United States)

We study infinite-horizon Markov decision processes (MDPs) with fast–slow structure, in which some state variables evolve rapidly (fast states), whereas others change more gradually (slow states). This structure commonly arises in practice when decisions must be made at high frequencies over long horizons and when slowly changing information still plays a critical role in determining optimal actions. Examples include inventory control under slowly changing demand indicators or dynamic pricing with gradually shifting consumer behavior. Modeling the problem at the natural decision frequency leads to MDPs with discount factors close to one, making them computationally challenging. We propose a novel approximation strategy that freezes slow states during phases of lower level planning and subsequently applies value iteration to an auxiliary upper level MDP that evolves on a slower timescale. Freezing states for short periods of time leads to easier to solve lower level problems, whereas a slower upper level timescale allows for a more favorable discount factor. On the theoretical side, we analyze the regret incurred by our frozen-state approach, and this leads to simple insights on how to trade off regret versus computational cost. Empirically, we benchmark our new frozen-state methods on three domains: (i) inventory control with fixed order costs, (ii) a grid world problem with spatial tasks, and (iii) dynamic pricing with reference price effects. We demonstrate that the new methods produce high-quality policies with significantly less computation, and we show that simply omitting slow states is often a poor heuristic. This paper was accepted by J. George Shanthikumar, data science. Funding: This research is based upon work supported by the U.S. National Science Foundation [Grant 1807536]. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2023.00012 .

Despite the demonstrated success of Pre-trained Language Models (PLM) in enhancing various recommendation tasks, their performance in friend recommendation systems, which are heavily influenced by complex social network dynamics, remains unproven. On the other hand, for social networks like Facebook, graph-based machine learning approaches in friend suggestion, like Graph Neural Networks (GNNs), struggle with the computational demands posed by social graphs. In is paper we investigate the application of PLM and GNN in the context of PYMK features within Facebook's social graph. We propose a representation learning scheme that captures both the local structure and semantic content within a second-degree connection space. Our approach leverages pre-trained transformer models with a feature aggregation scheme that enables efficient node representation learning in large social networks. We detail our model's architecture and discuss our training methods, accompanied by detailed experiments. Our model has improved the amount of friending on Facebook, facilitating new connections for users each day in online experiment.

We present an audio-driven real-time system for animating photorealistic 3D facial avatars with minimal latency, designed for social interactions in virtual reality for anyone. Central to our approach is an encoder model that transforms audio signals into latent facial expression sequences in real time, which are then decoded as photorealistic 3D facial avatars. Leveraging the generative capabilities of diffusion models, we capture the rich spectrum of facial expressions necessary for natural communication while achieving real-time performance (<15ms GPU time). Our novel architecture minimizes latency through two key innovations: an online transformer that eliminates dependency on future inputs and a distillation pipeline that accelerates iterative denoising into a single step. We further address critical design challenges in live scenarios for processing continuous audio signals frame-by-frame while maintaining consistent animation quality. The versatility of our framework extends to multimodal applications, including semantic modalities such as emotion conditions and multimodal sensors with head-mounted eye cameras on VR headsets. Experimental results demonstrate significant improvements in facial animation accuracy over existing offline state-of-the-art baselines, achieving 100 to 1000 × faster inference speed. We validate our approach through live VR demonstrations and across various scenarios such as multilingual speeches.

In recent times, the wireless network market has received an influx of innovative technologies to cope up with the ever-growing data traffic demand and make efficient deployment and utilization of network resources. Despite that, cellular service and coverage in non-urban areas still remains largely unreliable. Providers predominantly set up roaming agreements to offer service to their customers in such regions where they have no coverage. These roaming services come with their own set of technical and operational constraints and limitations. As an alternative, we introduce <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Wireless Peering</i> for cellular providers, a concept inspired by ISP peering in wireline networks. By facilitating <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">settlement-free</i> spectrum sharing, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Wireless Peering</i> allows providers to seamlessly extend their coverage to off-network regions, without any hardware modifications. Due to its software-defined nature, the model offers high scalability, cost-effectiveness and ease of deployment. In this paper, we detail the core ideas and operational framework of a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Wireless Peering</i> model with a particular emphasis on improving customer satisfaction and provider revenue gains. Simulation results using <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">OpencellID</i> data on real-life providers and customers across contiguous United States (US) exhibit significant improvements over roaming for both customers and providers.

ABSTRACT Micro organic light‐emitting diodes (microOLEDs) are gaining attention for next‐generation augmented reality (AR) and virtual reality (VR) applications due to their compact form factors and high pixel density. However, traditional multilayer thin‐film simulations—based on the assumption of dipole emitters embedded in infinite planar layers—fail to capture the three‐dimensional optical effects of microOLEDs. This is primarily due to their micrometer‐scale pixel size, which becomes comparable to the vertical dimensions of the device, and the presence of a pixel define layer (PDL). To address these limitations, finite element methods (FEM) and finite‐difference time‐domain (FDTD) methods are commonly employed. However, these methods typically demand substantial computational resources, limiting their uses to the illustration of specific optical characteristics and trends rather than enabling a full quantitative analysis. This study introduces an optimized FEM‐based simulation method for micro‐scale OLEDs embedded with multiple dipole sources. By incorporating randomly distributed dipole sources with varied positions, orientations, and relative phases, the proposed approach enables accurate far‐field radiation pattern calculations while significantly reducing computational burden and simulation time, offering a promising pathway toward comprehensive optical analysis of microOLEDs and thus improving the understanding of light extraction and propagation at the micro‐pixel level.

CUDA is the de facto programming model for GPUs, which is widely used in the domains of HPC and AI. To obtain bare-metal performance, vendors and academia develop various profiling tools to guide optimization. However, most existing tools focus on hotspot analysis with limited capabilities in identifying actionable opportunities. To complement existing tools, we present RedSan, a novel profiling tool that leverages binary instrumentation to identify redundant instructions in fully optimized CUDA programs. Guided by RedSan, we are able to optimize programs such as PolybenchGPU, Rodinia, PASTA, DARKNET, and LULESH, yielding up to a 6.27 × speedup and 3.00 × reduction in memory instructions.

Recent years have witnessed success of sequential modeling, generative recommender, and large language model for recommendation. Though the scaling law has been validated for sequential models, it showed inefficiency in computational capacity when considering real-world applications like recommendation, due to the non-linear(quadratic) increasing nature of the transformer model. To improve the efficiency of the sequential model, we introduced a novel approach to sequential recommendation that leverages personalization techniques to enhance efficiency and performance. Our method compresses long user interaction histories into learnable tokens, which are then combined with recent interactions to generate recommendations. This approach significantly reduces computational costs while maintaining high recommendation accuracy. Our method could be applied to existing transformer based recommendation models, e.g., HSTU and HLLM. Extensive experiments on multiple sequential models demonstrate its versatility and effectiveness. Source code is available at https://github.com/facebookresearch/PerSRec.

In this paper, we systemically disentangle BHG, a graph deep learning framework for daily users' ads recommendations. BHG mainly relies on two pillars: (1) graph tokenization to convert the input temporal heterogeneous graph into sequences of tokens, and (2) graph MLP-Mixer neural architecture to learn node representations on sequences of tokens via a mini-batch manner. In general, BHG embraces three advantages: (1) flexibility, i.e., BHG can be seamlessly integrated with any existing industrial recommendation model by treating the learned node embeddings as additional features that encode interactions, (2) efficiency, i.e., the graph tokenization allows sampling the neighborhood both locally and globally, and reduces the number of nodes considered for aggregations, and (3) model simplicity, i.e., the graph MLP-Mixer does not require self-attention for aggregating nodes and hence enjoys the simplicity. We demonstrate the superior performance of the proposed BHG on two internal datasets and one public dataset. We hope this paper can share insights and explain large-scale graph deep learning deployments for researchers, engineers, and practitioners.