233 citations · 328 across the 16 of their papers we have counts for
16 papers
Harnessing Synthetic Datasets: The Role of Shape Bias in Deep Neural Network Generalization
Elior Benarous, Sotiris Anagnostidis, Luca Biggio +1
Recent advancements in deep learning have been primarily driven by the use of large models trained on increasingly vast datasets. While neural scaling laws have emerged to predict…
Accelerating galaxy dynamical modeling using a neural network for joint lensing and kinematics analyses
Matthew R. Gomer, Sebastian Ertl, Luca Biggio +6
Strong gravitational lensing is a powerful tool to provide constraints on galaxy mass distributions and cosmological parameters, such as the Hubble constant, . Nevertheless, i…
Gemtelligence: Accelerating Gemstone classification with Deep Learning
Tommaso Bendinelli, Luca Biggio, Daniel Nyfeler +4
The value of luxury goods, particularly investment-grade gemstones, is greatly influenced by their origin and authenticity, sometimes resulting in differences worth millions of dol…
Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers
Sotiris Anagnostidis, Dario Pavllo, Luca Biggio +3
Autoregressive Transformers adopted in Large Language Models (LLMs) are hard to scale to long sequences. Despite several works trying to reduce their computational cost, most of LL…
Uncertainty Quantification in Machine Learning for Engineering Design and Health Prognostics: A Tutorial
Venkat Nemani, Luca Biggio, Xun Huan +6
On top of machine learning models, uncertainty quantification (UQ) functions as an essential layer of safety assurance that could lead to more principled decision making by enablin…
Controllable Neural Symbolic Regression
Tommaso Bendinelli, Luca Biggio, Pierre-Alexandre Kamienny
In symbolic regression, the goal is to find an analytical expression that accurately fits experimental data with the minimal use of mathematical symbols such as operators, variable…
An SDE for Modeling SAM: Theory and Insights
Enea Monzio Compagnoni, Luca Biggio, Antonio Orvieto +3
We study the SAM (Sharpness-Aware Minimization) optimizer which has recently attracted a lot of interest due to its increased performance over more classical variants of stochastic…
Cosmology from Galaxy Redshift Surveys with PointNet
Sotiris Anagnostidis, Arne Thomsen, Tomasz Kacprzak +4
In recent years, deep learning approaches have achieved state-of-the-art results in the analysis of point cloud data. In cosmology, galaxy redshift surveys resemble such a permutat…
Fast emulation of two-point angular statistics for photometric galaxy surveys
Marco Bonici, Luca Biggio, Carmelita Carbone +1
We develop a set of machine-learning based cosmological emulators, to obtain fast model predictions for the angular power spectrum coefficients characterising tomographic…
Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse
Lorenzo Noci, Sotiris Anagnostidis, Luca Biggio +3
Transformers have achieved remarkable success in several domains, ranging from natural language processing to computer vision. Nevertheless, it has been recently shown that stackin…
Dynaformer: A Deep Learning Model for Ageing-aware Battery Discharge Prediction
Luca Biggio, Tommaso Bendinelli, Chetan Kulkarni +1
Electrochemical batteries are ubiquitous devices in our society. When they are employed in mission-critical applications, the ability to precisely predict the end of discharge unde…
FIGARO: Generating Symbolic Music with Fine-Grained Artistic Control
Dimitri von Rütte, Luca Biggio, Yannic Kilcher +1
Generating music with deep neural networks has been an area of active research in recent years. While the quality of generated samples has been steadily increasing, most methods ar…
On the effectiveness of Randomized Signatures as Reservoir for Learning Rough Dynamics
Enea Monzio Compagnoni, Anna Scampicchio, Luca Biggio +3
Many finance, physics, and engineering phenomena are modeled by continuous-time dynamical systems driven by highly irregular (stochastic) inputs. A powerful tool to perform time se…
Time delay estimation in unresolved lensed quasars
L. Biggio, A. Domi, S. Tosi +4
Time-delay cosmography can be used to infer the Hubble parameter by measuring the relative time delays between multiple images of gravitationally-lensed quasars. A few of suc…
Neural Symbolic Regression that Scales
Luca Biggio, Tommaso Bendinelli, Alexander Neitz +2
Symbolic equations are at the core of scientific discovery. The task of discovering the underlying equation from a set of input-output pairs is called symbolic regression. Traditio…
Uncertainty-aware Remaining Useful Life predictor
Luca Biggio, Alexander Wieland, Manuel Arias Chao +2
Remaining Useful Life (RUL) estimation is the problem of inferring how long a certain industrial asset can be expected to operate within its defined specifications. Deploying succe…