Portrait of Stefano Massaroli is unavailable

Stefano Massaroli

stefano.massaroli@mila.quebec
Postdoctorate - Université de Montréal
Supervisor
Yoshua Bengio

Publications

Improving *day-ahead* Solar Irradiance Time Series Forecasting by Leveraging Spatio-Temporal Context
Oussama Boussif
Ghait Boukachab
Dan Assouline
Stefano Massaroli
Tianle Yuan
Loubna Benabbou
Yoshua Bengio
Solar power harbors immense potential in mitigating climate change by substantially reducing CO…
openreview.net
Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions
Stefano Massaroli
Michael Poli
Daniel Y Fu
Hermann Kumbong
Rom Nishijima Parnichkun
Aman Timalsina
David W. Romero
Quinn McIntyre
Beidi Chen
Atri Rudra
Ce Zhang
Christopher Re
Stefano Ermon
Yoshua Bengio
Recent advances in attention-free sequence models rely on convolutions as alternatives to the attention operator at the core of Transformers… (see more). In particular, long convolution sequence models have achieved state-of-the-art performance in many domains, but incur a significant cost during auto-regressive inference workloads -- naively requiring a full pass (or caching of activations) over the input sequence for each generated token -- similarly to attention-based models. In this paper, we seek to enable
openreview.net
What if We Enrich day-ahead Solar Irradiance Time Series Forecasting with Spatio-Temporal Context?
Oussama Boussif
Ghait Boukachab
Dan Assouline
Stefano Massaroli
Tianle Yuan
Loubna Benabbou
Yoshua Bengio
The global integration of solar power into the electrical grid could have a crucial impact on climate change mitigation, yet poses a challen… (see more)ge due to solar irradiance variability. We present a deep learning architecture which uses spatio-temporal context from satellite data for highly accurate day-ahead time-series forecasting, in particular Global Horizontal Irradiance (GHI). We provide a multi-quantile variant which outputs a prediction interval for each time-step, serving as a measure of forecasting uncertainty. In addition, we suggest a testing scheme that separates easy and difficult scenarios, which appears useful to evaluate model performance in varying cloud conditions. Our approach exhibits robust performance in solar irradiance forecasting, including zero-shot generalization tests at unobserved solar stations, and holds great promise in promoting the effective use of solar power and the resulting reduction of CO
2023-07-28
ICML.cc/2023/Workshop/SynS_and_ML (published)
openreview.net
openreview.net
What if We Enrich day-ahead Solar Irradiance Time Series Forecasting with Spatio-Temporal Context?
Oussama Boussif
Ghait Boukachab
Dan Assouline
Stefano Massaroli
Tianle Yuan
Loubna Benabbou
Yoshua Bengio
2023-07-28
ICML.cc/2023/Workshop/SynS_and_ML (published)
doi.org
openreview.net
Hyena Hierarchy: Towards Larger Convolutional Language Models
Michael Poli
Stefano Massaroli
Eric Nguyen
Daniel Y Fu
Tri Dao
Stephen Baccus
Yoshua Bengio
Stefano Ermon
Christopher Re
2023-04-24
ICML.cc/2023/Conference (poster)
doi.org
openreview.net
Hyena Hierarchy: Towards Larger Convolutional Language Models
Michael Poli
Stefano Massaroli
Eric Nguyen
Daniel Y Fu
Tri Dao
Stephen Baccus
Yoshua Bengio
Stefano Ermon
Christopher Re
Recent advances in deep learning have relied heavily on the use of large Transformers due to their ability to learn at scale. However, the c… (see more)ore building block of Transformers, the attention operator, exhibits quadratic cost in sequence length, limiting the amount of context accessible. Existing subquadratic methods based on low-rank and sparse approximations need to be combined with dense attention layers to match Transformers at scale, indicating a gap in capability. In this work, we propose Hyena, a subquadratic drop-in replacement for attention constructed by interleaving implicitly parametrized long convolutions and data-controlled gating. In challenging reasoning tasks on sequences of thousands to hundreds of thousands of tokens, Hyena improves accuracy by more than 50 points over operators relying on state-space models, transfer functions, and other implicit and explicit methods, matching attention-based models. We set a new state-of-the-art for dense-attention-free architectures on language modeling in standard datasets WikiText103 and The Pile, reaching Transformer quality with a 20% reduction in training compute required at sequence length 2k. Hyena operators are 2x faster than highly optimized attention at sequence length 8k, with speedups of 100x at 64k.
2023-04-24
ICML.cc/2023/Conference (published)
doi.org
openreview.net
HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution
Eric Nguyen
Michael Poli
Marjan Faizi
Armin W Thomas
Callum Birch-Sykes
Michael Wornow
Aman Patel
Clayton M. Rabideau
Stefano Massaroli
Yoshua Bengio
Stefano Ermon
Stephen Baccus
Christopher Re
openreview.net