Episodes

  • TransAct Transformer-based Realtime User Action Model for Recommendation at Pinterest

    TransAct Transformer-based Realtime User Action Model for Recommendation at Pinterest
    Jul 8 2024
    Pinterest home feed reccomendation system. Needs to react to both long term interests + short term (even single session only) interests. Read full paper: https://arxiv.org/abs/2306.00248v1 Tags: Recommender Systems, Transformers, Systems and Performance
    Show more Show less
    Less than 1 minute
  • Zero Bubble Pipeline Parallelism

    Zero Bubble Pipeline Parallelism
    Jul 8 2024
    Core idea is think about backward pass into two flows, one to compute grad wrt to parameters, and one to compute grad wrt to output of last layer, schedule so that you are always working instead of waiting (bubble). Read full paper: https://arxiv.org/abs/2401.10241 Tags: Systems and Performance, Deep Learning, Machine Learning
    Show more Show less
    Less than 1 minute
  • The limits to learning a diffusion model

    The limits to learning a diffusion model
    Jul 8 2024
    Don't be confused by the title, diffusion here is not referring to diffusion as we use it today in context of image generation process, but more about modelling diffusive processes (like virus spread) This paper answers the question about 'how much data do we need, before we can figure out the final affected value' turns out this is a lot more thant people expect. Read full paper: https://arxiv.org/abs/2006.06373 Tags: Generative Models, Machine Learning, Deep Learning
    Show more Show less
    Less than 1 minute
  • A Better Match for Drivers and Riders Reinforcement Learning at Lyft

    A Better Match for Drivers and Riders Reinforcement Learning at Lyft
    Jul 8 2024
    The paper demonstrates the successful application of reinforcement learning to improve the efficiency of driver-rider matching in ride-sharing platforms. The use of online RL allows for real-time adaptation, resulting in decreased wait times for riders, increased earnings for drivers, and overall higher user satisfaction. The research paves the way for more intelligent systems in the ride-sharing industry, with potential for further optimization and expansion into various other aspects of the ecosystem. Read full paper: https://arxiv.org/abs/2310.13810 Tags: Reinforcement Learning, Recommender Systems, Machine Learning
    Show more Show less
    Less than 1 minute
  • AutoEmb Automated Embedding Dimensionality Searchg in Streaming Recommendations

    AutoEmb Automated Embedding Dimensionality Searchg in Streaming Recommendations
    Jul 8 2024
    AutoEmb is about using different lenghts of embedding vectors for different items, use less memory + potentially learn more robust stuff for items with less data, and learn more nuanced stuff for popular items. Read full paper: https://arxiv.org/abs/2002.11252 Tags: Deep Learning, Recommender Systems, Optimization
    Show more Show less
    Less than 1 minute
  • NeuralProphet Explainable Forecasting at Scale

    NeuralProphet Explainable Forecasting at Scale
    Jul 8 2024
    '_Successor_' of Prophet (by facebook) for time series modelling. Read full paper: https://arxiv.org/abs/2111.15397 Tags: Deep Learning, Machine Learning, Explainable AI
    Show more Show less
    Less than 1 minute
  • No-Transaction Band Network A Neural Network Architecture for Efficient Deep Hedging

    No-Transaction Band Network A Neural Network Architecture for Efficient Deep Hedging
    Jul 8 2024
    The paper introduces a deep hedging approach using neural networks to optimize hedging strategies for derivatives in imperfect markets. The key takeaway is the development of the 'no-transaction band network' to address action dependence and improve efficiency in hedging, showcasing superior performance compared to traditional methods in terms of expected utility and price efficiency, and faster training. Future research focuses on addressing limitations such as non-linear transaction costs and discontinuous payoffs, as well as challenges in data availability and model explainability for real-world applications. Read full paper: https://arxiv.org/abs/2103.01775 Tags: Deep Learning, AI for Science, Machine Learning
    Show more Show less
    Less than 1 minute
  • ZeRO Memory Optimizations: Toward Training Trillion Parameter Models

    ZeRO Memory Optimizations: Toward Training Trillion Parameter Models
    Jul 8 2024
    The paper introduces ZeRO, a novel approach to optimize memory usage when training massive language models. ZeRO-DP and ZeRO-R components effectively reduce memory redundancy and allow for training models with up to 170 billion parameters efficiently. The technique shows superlinear scalability, user-friendly implementation, and has the potential to democratize large model training in AI research. Read full paper: https://arxiv.org/abs/1910.02054 Tags: Systems and Performance, Deep Learning, Natural Language Processing
    Show more Show less
    Less than 1 minute