LDLuke Nicholas Darlow

Luke Nicholas Darlow

*This is an algorithmically generated author record based on publicly available information.

Luke Nicholas Darlow has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Serverless Cold Starts and Where to Find Them

    by Artjom Joosen, Ahmed Hassan, Martin Asenov, Rajkarn Singh, Luke Darlow, Jianfeng Wang, Qiwen Deng, Adam Barker


  • Top Cited Papers
    Open Access

    How Does It Function? Characterizing Long-term Trends in Production Serverless Workloads

    by Artjom Joosen, Ahmed Hassan, Martin Asenov, Rajkarn Singh, Luke Darlow, Jianfeng Wang, Adam Barker


  • Open Access

    TSMix: time series data augmentation by mixing sources

    by Luke Nicholas Darlow, Artjom Joosen, Martin Asenov, Qiwen Deng, Jianfeng Wang, Adam Barker

    Data augmentation for time series is challenging because of the complex multi-scale relationships spanning ordered continuous sequences: one cannot easily alter a single datum and expect these relationships to be preserved. Time series datum are not independent and identically distributed random variables. However, modern Function as a Service (FaaS) infrastructure yields a unique opportunity for data augmentation because of the multiple distinct functions within a single data source. Further, common strong periodicity afforded by the human diurnal cycle and its link to these data sources enables mixing distinct functions to form pseudo-functions for improved model training. Herein we propose time series mix (TSMix), where pseudo univariate time series are created by mixing combinations of real univariate time series. We show that TSMix improves the performance on held-out test data for two state-of-the-art forecast models (N-BEATS and N-HiTS) and linear regression.


  • Open Access

    FoldFormer: sequence folding and seasonal attention for fine-grained long-term FaaS forecasting

    by Luke Nicholas Darlow, Artjom Joosen, Martin Asenov, Qiwen Deng, Jianfeng Wang, Adam Barker

    Fine-grained long-term (FGLT) time series forecasting is a fundamental challenge in Function as a Service (FaaS) platforms. The data that FaaS function requests produce are fine-grained (per-second/minute), often have daily periodicity, and are persistent over the long term. Forecasting in the FGLT data regime is challenging, and Transformer models can scale poorly for long sequences. We propose FoldFormer that combines several novel elements - time-to-latent folding, seasonal attention, and convolutions over FFT representations - as a new solution for FGLT forecasting of FaaS function requests. FoldFormer is designed to efficiently consume very fine-grained multi-day data with nearly no additional model, memory, or compute overhead, when compared to consuming coarse-grained data. We show either state-of-the-art or competitive performance for per-minute function requests on the top 5 most requested functions for three data sources, including two in-house Huawei Cloud sources and Azure 2019. We also show state-of-the-art performance at per-second granularity --- a regime that critically limits most other methods.


  • Open Access

    What Information Does a ResNet Compress?

    by Luke Nicholas Darlow, Amos Storkey

    The information bottleneck principle (Shwartz-Ziv & Tishby, 2017) suggests that SGD-based training of deep neural networks results in optimally compressed hidden layers, from an information theoretic perspective. However, this claim was established on toy data. The goal of the work we present here is to test whether the information bottleneck principle is applicable to a realistic setting using a larger and deeper convolutional architecture, a ResNet model. We trained PixelCNN++ models as inverse representation decoders to measure the mutual information between hidden layers of a ResNet and input image data, when trained for (1) classification and (2) autoencoding. We find that two stages of learning happen for both training regimes, and that compression does occur, even for an autoencoder. Sampling images by conditioning on hidden layers' activations offers an intuitive visualisation to understand what a ResNets learns to forget.