Carlos Bravo-Prieto @charl_bp

Postdoctoral Researcher Quantum Computing @ Freie Universität Berlin bpcarlos.github.io Joined August 2018

Tweets

235
Followers

862
Following

298
Likes

2K

Jens Eisert @jenseisert

3 months ago

A PAC-Bayesian approach to generalization for quantum models. We take steps towards non-uniform and data-dependent bounds for generalization of quantum machine learning models. scirate.com/arxiv/2603.229… In detail, #generalization is a central concept in machine learning theory, yet for quantum models, it is predominantly analyzed through uniform bounds that depend on a model's overall capacity rather than the specific function learned. These capacity-based uniform bounds are often too loose and entirely insensitive to the actual training and learning process. Previous theoretical guarantees have failed to provide #nonuniform, data-dependent bounds that reflect the specific properties of the learned solution rather than the worst-case behavior of the entire hypothesis class. To address this limitation, we derive the first #PACBayesian generalization bounds for a broad class of quantum models by analyzing layered circuits composed of general quantum channels, which include dissipative operations such as mid-circuit measurements and feedforward. Through a channel perturbation analysis, we establish non-uniform bounds that depend on the norms of learned parameter matrices; we extend these results to symmetry-constrained equivariant quantum models; and we validate our theoretical framework with numerical experiments. This work provides actionable model design insights and establishes a foundational tool for a more nuanced understanding of generalization in #quantummachinelearning. Warm thanks to the team of @pablones8, Matthias C. Caro, @EliesMiquel, @FJSchreiber, and @charl_bp for this great collaboration.

2 7 25 2K 2

View Details

Jens Eisert @jenseisert

6 months ago

We suggest a shift in emphasis—namely, putting it on the representability of #functions—when thinking about quantum models aimed at achieving a quantum advantage for machine learning tasks. scirate.com/arxiv/2512.156… Demonstrating quantum advantage in #machinelearning tasks requires navigating a complex landscape of proposed models and algorithms. To bring clarity to this search, we introduce a framework that connects the structure of #parametrizedquantumcircuits to the mathematical nature of the functions they can actually learn. Within this framework, we show how fundamental properties, like circuit depth and non-Clifford gate count, directly determine whether a model's output leads to efficient classical simulation or #surrogation. We argue that this analysis uncovers common pathways to dequantization that underlie many existing simulation methods. More importantly, it reveals critical distinctions between models that are fully simulatable, those whose function space is classically tractable, and those that remain robustly quantum. This perspective provides a conceptual map of this landscape, clarifying how different models relate to classical simulability and pointing to where opportunities for quantum advantage may lie. Warm thanks to @sergiml, @EliesMiquel, Carlos Bravo-Prieto, and Tommaso Guaita for this wonderful collaboration.

2 9 59 3K 16

View Details

Alba Cervera-Lierta @albaclierta

a year ago

I'm looking for a postdoc to work on Quantum-HPC applications, in particular (but not exclusive) to those related with adiabatic quantum computing and annealing. Apply here 👇 bsc.es/join-us/job-op… @BSC_CNS #quantumcomputing

0 14 27 2K 6

View Details

Elies Gil-Fuster @EliesMiquel

a year ago

📢 Check out @charl_bp's post on our new work out today! We tackle a modern #ML question: will quantum machine learning models #QML show double descent? This is an important question, as Carlos explains 👇🧵 scirate.com/arxiv/2501.100… Kudos and thanks for the awesome collaboration!

Carlos Bravo-Prieto @charl_bp

a year ago

Excited to share our latest research on double descent in quantum machine learning, now on arXiv! 📜 Check it out: scirate.com/arxiv/2501.100… We explore how large quantum models do not necessarily lead to reduced performance on unseen data🧵

2 2 18 2K 4

0 1 18 707 1

View Details

Carlos Bravo-Prieto @charl_bp

a year ago

Huge thanks to my incredible co-authors: Marie Kempkes, Aroosa Ijaz, Elies Gil-Fuster (@EliesMiquel), Jakob Spiegelberg, Evert van Nieuwenburg, and Vedran Dunjko.

0 0 2 122 0

View Details

Carlos Bravo-Prieto @charl_bp

a year ago

Why is this important? This shows quantum models can perform well in overparameterized regimes. But this isn’t the end of the story—test error after the double descent peak isn’t guaranteed to be better than before. Careful design of quantum models remains critical!

1 0 2 128 0

View Details

Carlos Bravo-Prieto @charl_bp

a year ago

2 2 18 2K 4

View Details

Diego García-Martín @DiegoGM_quantum

a year ago

Our work featuring high approximation ratios in MaxCut using a reduced number of qubits has been published in @NatureComms ! 🎉🎉 nature.com/articles/s4146…

0 1 35 960 5

View Details

Marco Cerezo @MvsCerezo

2 years ago

🚨Applications for LANL's 2025 Quantum Computing Summer School are open! Please apply here 👇 …l-summer-school-programs.wizehive.app/program/quantu… Reposts appreciated!

3 32 67 13K 27

View Details

QCTiP2025 @QCTiP2025

2 years ago

Submissions for QCTiP 2025 are now open.

1 16 31 11K 10

View Details

Jens Eisert @jenseisert

2 years ago

Learning complexity gradually in quantum machine learning models scirate.com/arxiv/2411.119… #Quantummachinelearning is growing up and increasingly making use of classical machine learning ideas.

3 18 69 3K 17

View Details

QCTiP2025 @QCTiP2025

2 years ago

We are thrilled to announce that the 6th edition of QCTiP will be in Berlin on the 23-25 April!

5 17 43 9K 6

View Details

Jens Eisert @jenseisert

2 years ago

Come work with us! We offer another round of attractive #postdocposition|s and #PhDposition|s in #quantuminformationtheory, on topics ranging from abstract #mathematical themes to pragmatically motivated questions, in an open and stimulating discussion climate. Topics include - #quantuminformationtheory, - #quantumerrorcorrection, - #tensornetworks, - #quantumalgorithms. physik.fu-berlin.de/en/einrichtung…

25 25 144 28K 24

View Details

Zoe Holmes @qZoeHolmes

2 years ago

We’re looking for a post doc to join us exploring the intersection of quantum chemistry and quantum computing - 2 year position - Based in the QIC group at EPFL (Lausanne) - Collaboration with Roche (Basel) Email me if interested

4 41 193 24K 36

View Details

Sumeet Khatri @SumeetKhatri6

2 years ago

I've started a new position! Starting this fall, I'm an Assistant Professor in the CS department @virginia_tech @VT_CS, with open PhD and postdoc positions! Check out my research (sumeetkhatri.com/research/), and feel free to contact me if you, or anyone you know, is interested.

6 13 75 6K 3

View Details

Carlos Bravo-Prieto @charl_bp

2 years ago

@pablones8 @EliesMiquel @IMathYou2 It was great having you here! Looking forward to keeping up our collaboration.

0 0 4 136 0

View Details

Pablo Rodríguez Grasa @pablones8

2 years ago

And today two great months of a lot of learning in Berlin come to an end. Many thanks to @charl_bp for hosting me and giving me the opportunity to work on such an interesting project. Also, special thanks to the great @EliesMiquel and @IMathYou2 for the amazing discussions.