Scholar
Nicola Muça Cirone
Google Scholar ID: jjm12qUAAAAJ
PhD Student, Imperial College London
Citations & Impact
Citations
92
H-index
3
i10-index
2
Publications
9
Co-authors
5
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Reviewed Publications: 1. Walker, Yang, Muça Cirone, Salvi, Lyons. 'Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models', NeurIPS25 (Spotlight); 2. Movahedi, Sarnthein, Muça Cirone, Orvieto. 'Fixed-Point RNNs: From Diagonal to Dense in a Few Iterations', NeurIPS25 (Spotlight); 3. Muça Cirone, Orvieto, Walker, Salvi, Lyons. 'Theoretical Foundations of Deep Selective State-Space Models', NeurIPS24; 4. Muça Cirone, Lemercier, Salvi. 'Neural signature kernels as infinite-width-depth-limits of controlled ResNets', ICML23. Preprints: 1. Futter, Muça Cirone, Horvath. 'Kernel Learning for Mean-Variance Trading Strategies', July 2025; 2. Muça Cirone, Salvi. 'ParallelFlow: Parallelizing Linear Transformers via Flow Discretization', February 2025; 3. Glückstad, Muça Cirone, Teichmann. 'Signature Reconstruction from Randomized Signatures', February 2025; 4. Muça Cirone, Salvi. 'Rough kernel hedging', January 2025; 5. Muça Cirone, Hamdan, Salvi. 'Graph Expansions of Deep Neural Networks and their Universal Scaling Limits', August 2024.
Research Experience
- February to March 2025: Interned at Cartesia.ai as a PhD Researcher, working on distillation and multimodality; July to September 2025: Interned at Quadrature Capital, did lots of quanty things that are not allowed to share.
Education
- PhD: Oxford-Imperial CDT in Mathematics of Random Systems, Advisor: Dr. Cristopher Salvi, Time: Ongoing; BSc: Università di Pisa, Advisor: Professor Josef Teichmann, Time: 2022.
Background
- Research Interests: Time series analysis, Machine Learning, Mathematical Finance; Specialties: Rough Paths Theory, Functional and Stochastic Analysis; Brief Introduction: Currently pursuing a PhD at the Oxford-Imperial CDT, focusing on exploring the scaling laws governing the behavior of randomly initialized Neural Networks.
Miscellany
- Quote: 'Spernimus obvia, ex quibus tamen non obvia sequuntur' - Leibniz
