Quantum Theory and Application of Contextual Optimal Transport
Authors: Nicola Mariella, Albert Akhriev, Francesco Tacchino, Christa Zoufal, Juan Carlos Gonzalez-Espitia, Benedek Harsanyi, Eugene Koskin, Ivano Tavernelli, Stefan Woerner, Marianna Rapsomaniki, Sergiy Zhuk, Jannis Born
ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We verify our method (Qont OT) on synthetic and real data by predicting variations in cell type distributions conditioned on drug dosage. Importantly we conduct a 24-qubit hardware experiment on a task challenging for classical computers and report a performance that cannot be matched with our classical neural OT approach. |
| Researcher Affiliation | Collaboration | Nicola Mariella 1 Albert Akhriev 1 Francesco Tacchino 2 Christa Zoufal 2 Juan Carlos Gonzalez-Espitia 2 3 Benedek Harsanyi 4 5 Eugene Koskin 1 6 Ivano Tavernelli 2 Stefan Woerner 2 Marianna Rapsomaniki 4 Sergiy Zhuk 1 Jannis Born 4 1IBM Quantum, IBM Research Europe Dublin 2IBM Quantum, IBM Research Europe Zurich, Switzerland 3Politecnico di Milano, Milan, Italy 4IBM Research, IBM Research Europe Zurich, Switzerland 5École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland 6University College Dublin, Ireland. |
| Pseudocode | No | The paper describes methods and circuit structures but does not include any clearly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | No explicit statement about open-sourcing the code or a link to a code repository for the described methodology was found. |
| Open Datasets | Yes | We applied our method on predicting changes in the composition of a cell population due to drug perturbations and tested it on synthetic and real data as shown in Figure 3. Starting from a population of heterogeneous cells, each living in a high-dimensional state space we know that administering a drug has a direct effect on the composition of the cell population, by eliminating certain cell types or pushing some other cell types to proliferate. We denote as µ, νi the cell type distribution of a cell population before and after the drug perturbation with a context variable pi, i.e., the drug dosage [0, 1]. We measure performance on unseen dosages for different data splitting strategies." and "Leveraging the established sc-RNA-seq generator Splatter (Zappia et al., 2017), we devised a perturbation data generator that allows to control the number of generated cells, genes, cell types, perturbation functions and more." and "To facilitate comparison with prior art, we compared Qont OT to Cell OT (Bunne et al., 2023) and Cond OT (Bunne et al., 2022) on two drugs from the Sci Plex dataset (Srivatsan et al., 2020) each administered in four dosages. |
| Dataset Splits | Yes | For each of the dosages and the control condition, 20% of cells were randomly held out for validation. |
| Hardware Specification | Yes | Parameters were optimized for 235 steps over 13 days on a 127-qubit device (IBM Sherbrooke) available through the IBM Quantum Platform. |
| Software Dependencies | Yes | In practice, we implemented two ansätze, centrosymmetric and simple. Both of them have been trained in Qiskit 0.43.0 (Qiskit contributors, 2023) and all experiments were performed with Qiskit s sampler class and, unless indicated otherwise (cf. Section 5.3), in statevector simulation." and "Cell OT and Cond OT are trained with the ott-jax package (Cuturi et al., 2022) for 1000 iterations and batches of size 50 on µi, i.e., the same 8-dimensional feature vectors (denoting a distribution of cell types over 50 cells) used to train Qont OT. |
| Experiment Setup | Yes | The sinkhorn regularization γ = 0.001. For the linear case, fp1(x) = 3x + 1 and for the non-linear case fp2(x) = 100x 0.2." and "We cluster with k-Means and k = d = 8 or 16" and "We use a cosine decay learning rate scheduler with an initial value of 0.001 and an alpha of 0.01, optimized with ADAM (Kingma & Ba, 2014)." and "a dropout (40%, unless indicated otherwise) |