Poster: https://cpal.cc/assets/CFP_CPAL_2024.pdf

### Overview

The Conference on Parsimony and Learning (CPAL) is an annual research conference focused on addressing the **parsimonious, low dimensional structures that** prevail in machine learning, signal processing, optimization, and beyond. We are interested in theories, algorithms, applications, hardware and systems, as well as scientific foundations for learning with parsimony.  We envision the conference as a general scientific forum where researchers in machine learning, applied mathematics, signal processing, optimization, intelligent systems, and all associated science and engineering fields can gather, share insights, and ultimately work towards a common modern theoretical and computational framework for understanding intelligence and science from the perspective of parsimonious learning.

See more about the new conference’s vision: https://cpal.cc/vision/

### Topics of Interest

Topics of interest include—but are not limited to—the following subject areas (Detailed: https://cpal.cc/subject_areas/):

* Theory & Foundation:   Theories for sparse coding, structured sparsity, subspace learning, low-dimensional manifolds, and general low-dimensional structures;  dictionary learning and representation learning for low-dimensional structures and their connections to deep learning theory; equivariance and invariance modeling; theoretical neuroscience and cognitive science foundation for parsimony, and biologically inspired computational mechanisms.
* Optimization & Algorithms:   Optimization, robustness, and generalization methods for learning compact and structured representations; interpretable and efficient deep architectures (e.g., based on unrolled optimization); data-efficient and computation-efficient training and inference; adaptive and robust learning and inference algorithms; Other nonlinear dimension-reduction and representation-learning methods.
* Data, Systems & Applications:   Domain-specific datasets, benchmarks, and evaluation metrics; parsimonious and structured representation learning from data; inverse problems that benefit from parsimonious priors; hardware and system co-design for parsimonious learning algorithms; parsimonious learning in intelligent systems that integrate perception-action cycles; applications in science, engineering, medicine, and social sciences.

The above is a high-level overview of CPAL's focus and is not intended to be exhaustive. If you are unsure whether your paper is a good fit for the conference, feel free to contact the program chairs via email (pcs@cpal.cc).

### Submission Tracks

We will have a main proceeding track (archival), and a “recent spotlight” track (non-archival). The OpenReview submission site can be found here: https://openreview.net/group?id=CPAL.cc/2024/Conference. Submissions to both tracks are to be prepared using the CPAL LaTeX style files (https://cpal.cc/assets/CPAL-2024-template.zip).

Proceeding track (**archival**): The submission and review stage is **double-blind**. We use OpenReview to host papers and allow for public discussions. Full proceedings papers can have up to nine pages with unlimited pages for references and appendix.

“Recent Spotlight” Track (**non-archival**): Submit a conference-style paper (at most nine pages, with extra pages for references) describing the work. Please also upload a short (250 word) abstract to OpenReview. OpenReview submissions may also include any of the following supplemental materials that describe the work in further detail:

* A poster (in PDF form) presenting results of work-in-progress.
* A link to an arXiv preprint or a blog post (e.g., distill.pub, Medium) describing results.
* Appendices with detailed derivations and additional experiments.

This track is non-archival and has no proceedings. We permit under-review or concurrent submissions, as well as papers officially accepted by a journal or conference within 6 months of the  Submission Deadline for Recent Spotlight Track (this year Oct 10, 2023). Reviewing will be performed in a **single-blind** fashion (authors should not anonymize their submissions).

**Notable Innovations in Our Review Mechanism**: An action PC will shepherd each paper. For every accepted paper, the names of its AC and action PC will be publicly released on its OpenReview page, for accountability. For every rejected paper (excluding withdrawals), only the name of its action PC will be displayed. Reviewers will be rated and dynamically selected.

Please see more details on our website (https://cpal.cc/review_guidelines/).

### Important Dates

All deadlines are 11:59PM UTC-12:00 Anywhere on Earth (https://www.timeanddate.com/time/zones/aoe)

* August 28th, 2023: Submission Deadline for Proceeding Track
* October 10th, 2023: Submission Deadline for Recent Spotlight Track
* October 14th, 2023: 2-Week Rebuttal Stage Starts (Proceeding Track)
* October 27th, 2023: Rebuttal Stage Ends, Authors-Reviewers Discussion Stage Starts  (Proceeding Track)
* November 5th, 2023: Authors-Reviewers Discussion Stage Ends  (Proceeding Track)
* November 20th, 2023: Final Decisions Released (Both Tracks)
* December 5th, 2023: Camera Ready Deadline (Both Tracks)
* January 3rd – 6th, 2024: Main Conference (In-Person, HKU Main Campus)

### Keynote Speakers

* Dan Alistarh, IST Austria/Neural Magic
* SueYeon Chung, NYU / Flatiron Institute
* Kostas Daniilidis, UPenn
* Maryam Fazel, University of Washington
* Tom Goldstein, University of Maryland
* Yingbin Liang, Ohio State University
* Robert D. Nowak, University of Wisconsin-Madison
* Dimitris Papailiopoulos, University of Wisconsin-Madison
* Jong Chul Ye, KAIST

### Organizers and Contact

For inquiries, please contact organizers: pcs@cpal.cc

Follow us:
Twitter: https://twitter.com/CPALconf
LinkedIn: https://www.linkedin.com/company/conference-on-parsimony-and-learning-cpal/
Slack: https://join.slack.com/t/cpal-conference/shared_invite/zt-1v5fvzv6a-nCA0cgIN24da3gbVDjlWbg

 list please contact: koroniioanna@csd.auth.gr List moderation is supervised by Prof. I.Pitas (pitas@csd.auth.gr).