Skip to yearly menu bar Skip to main content

NeurIPS 2024

Palais des Congrès de Montréal, Montréal CANADA
Sun Dec 2nd through Sat the 8th

Call For Papers 

Submission deadline: Fri May 18, 2018 20:00 PM UTC

Submit at:

The site will start accepting submissions about two weeks before the submission deadline.

Authors will be required to confirm that their submissions accord with the NeurIPS code of conduct.

Submissions are solicited for the Thirty-Second Annual Conference on Neural Information Processing Systems (NIPS/NeurIPS 2018), a multi track, interdisciplinary conference that brings together researchers in machine learning, computational neuroscience, and their applications.

Subject areas include:

  1. Algorithms: Active Learning; Adaptive Data Analysis; AutoML; Bandit Algorithms; Boosting and Ensemble Methods; Classification; Clustering; Collaborative Filtering; Components Analysis (e.g., CCA, ICA, LDA, PCA); Density Estimation; Dynamical Systems; Kernel Methods; Large Margin Methods; Metric Learning; Missing Data; Model Selection and Structure Learning; Multitask and Transfer Learning; Nonlinear Dimensionality Reduction and Manifold Learning; Online Learning; Ranking and Preference Learning; Regression; Relational Learning; Representation Learning; Semi-Supervised Learning; Similarity and Distance Learning; Sparse Coding and Dimensionality Expansion; Sparsity and Compressed Sensing; Spectral Methods; Stochastic Methods; Structured Prediction; Unsupervised Learning.

  2. Applications: Activity and Event Recognition; Audio and Speech Processing; Body Pose, Face, and Gesture Analysis; Communication- or Memory-Bounded Learning; Computational Biology and Bioinformatics; Computational Photography; Computational Social Science; Computer Vision; Denoising; Dialog- or Communication-Based Learning; Fairness, Accountability, and Transparency; Game Playing; Hardware and Systems; Image Segmentation; Information Retrieval; Matrix and Tensor Factorization; Motor Control; Music Modeling and Analysis; Natural Language Processing; Natural Scene Statistics; Network Analysis; Object Detection; Object Recognition; Privacy, Anonymity, and Security; Quantitative Finance and Econometrics; Recommender Systems; Robotics; Signal Processing; Source Separation; Speech Recognition; Sustainability; Systems Biology; Text Analysis; Time Series Analysis; Tracking and Motion in Video; Video Analysis; Video Segmentation; Visual Features; Visual Question Answering; Visual Scene Analysis and Interpretation; Web Applications and Internet Data.

  3. Data, Competitions, Implementations, and Software: Benchmarks; Competitions or Challenges; Data Sets or Data Repositories; Software Toolkits.

  4. Deep Learning: Adversarial Networks; Attention Models; Biologically Plausible Deep Networks; CNN Architectures; Deep Autoencoders; Efficient Inference Methods; Efficient Training Methods; Embedding Approaches; Few-Shot Learning Approaches; Generative Models; Interaction-Based Deep Networks; Memory-Augmented Neural Networks; Meta-Learning; Neural Abstract Machines; Optimization for Deep Networks; Predictive Models; Program Induction; Recurrent Networks; Supervised Deep Networks; Virtual Environments; Visualization or Exposition Techniques for Deep Networks.

  5. Neuroscience and Cognitive Science: Auditory Perception; Brain Imaging; Brain Mapping; Brain Segmentation; Brain--Computer Interfaces and Neural Prostheses; Cognitive Science; Connectomics; Human or Animal Learning; Language for Cognitive Science; Memory; Neural Coding; Neuropsychology; Neuroscience; Perception; Plasticity and Adaptation; Problem Solving; Reasoning; Spike Train Generation; Synaptic Modulation; Visual Perception.

  6. Optimization: Combinatorial Optimization; Convex Optimization; Non-Convex Optimization; Submodular Optimization.

  7. Probabilistic Methods: Bayesian Nonparametrics; Bayesian Theory; Belief Propagation; Causal Inference; Distributed Inference; Gaussian Processes; Graphical Models; Hierarchical Models; Latent Variable Models; MCMC; Topic Models; Variational Inference.

  8. Reinforcement Learning and Planning: Decision and Control; Exploration; Hierarchical RL; Markov Decision Processes; Model-Based RL; Multi-Agent RL; Navigation; Planning; Reinforcement Learning.

  9. Theory: Competitive Analysis; Computational Complexity; Control Theory; Frequentist Statistics; Game Theory and Computational Economics; Hardness of Learning and Approximations; Information Theory; Large Deviations and Asymptotic Analysis; Learning Theory; Regularization; Spaces of Functions and Kernels; Statistical Physics of Learning.

All submissions must be in PDF format. Submissions are limited to eight content pages, including all figures and tables, in the NeurIPS “submission” style; additional pages containing only references are allowed. Reviewing will be double blind; all submissions must be anonymized. Camera-ready papers will be due in advance of the conference; however, authors will be allowed to make minor changes, such as fixing typos or adding references, for a short period of time after the conference.

Author guidelines can be found here.

Frequently asked questions can be found here.

Supplementary material: Authors may submit up to 100MB of supplementary material, such as proofs, derivations, data, or source code; all supplementary material must be in PDF or ZIP format. Looking at supplementary material is at the discretion of the reviewers.

Reviewing: The reviewing process will be double blind at the level of reviewers and area chairs (i.e., reviewers and area chairs cannot see author identities) but not at the level of senior area chairs and program chairs. Authors will have a one-week opportunity to view and respond to initial reviews during the reviewing process. After decisions have been made, reviews, meta-reviews, and author responses for accepted submissions will be made public (but reviewer, area chair, and senior area chair identities will remain anonymous). Authors of rejected submissions will also have the option of making their submissions, reviews, meta-reviews, and author responses public if they wish (again, reviewer, area chair, and senior area chair identities will remain anonymous).

Evaluation criteria: Submissions that violate the NeurIPS style or page limits, are not within the scope of NeurIPS (see subject areas above), are in submission elsewhere, or have already been published elsewhere may be rejected without further review. Submissions that have fatal flaws revealed by the reviewers—including (without limitation) incorrect proofs or flawed or insufficient wet-lab, hardware, or software experiments—may be rejected on that basis, without taking into consideration other criteria. Other submissions will be judged on the basis of their technical quality, novelty, potential impact, and clarity. Typical NeurIPS papers often (but not always) include a mix of algorithmic, theoretical, and experimental results, in varying proportions. While theoretically grounded arguments are certainly welcome, it is counterproductive to add “decorative math” whose primary purpose is to make the submission look more substantial or even intimidating, without adding significant insight. Algorithmic contributions should have at least an illustration of how the algorithm might eventually materialize into a machine learning application.

Preprints: Non-anonymous preprints (on arXiv, social media, websites, etc.) are permitted, though preprints in the NeurIPS style must use the new “preprint” option, rather than the “final” option. Reviewers will be instructed not to actively look for such preprints, but encountering them will not constitute a conflict of interest. Authors may submit work to NeurIPS that is already available as a preprint (e.g., on arXiv) without citing it; however, previously published papers by the authors on related topics must be cited (with adequate anonymization to preserve double-blind reviewing).

Dual submissions: Dual submissions will be identified via a combination of automated methods and human (reviewer, area chair, senior area chair, program chair) judgment. NeurIPS coordinates with other conferences to identify dual submissions. Submissions that are identical or substantially similar to papers that are in submission to, have been accepted to, or have been published in other archival conferences, journals, workshops, etc. will be deemed dual submissions. Submissions that are identical or substantially similar to other NeurIPS submissions will also be deemed dual submissions; submissions should be distinct and sufficiently substantial. Note that slicing contributions too thinly may result in submissions being deemed dual submissions. The program chairs reserve the right to reject all NeurIPS submissions by all authors of dual submissions, not just those deemed dual submissions. The NeurIPS policy on dual submissions applies for the entire duration of the reviewing process (i.e., from the submission deadline to the notification date). Authors should contact the program chairs if they need further clarification.

Competitions, Demonstrations, Tutorials, and Workshops: There are separate competition and demonstration tracks at NeurIPS. Authors who wish to submit to these tracks should consult the appropriate calls. There are also separate calls for tutorials, and workshops.