NIPS workshop focuses on ML for developing countries.
problem Addressing machine learning challenges in developing nations.
method Not specified in the abstract.
result Not specified in the abstract.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,181 papers · 148 categories
Trend · papers per month
48 results for “NIPS papers”
NIPS 2018 Adversarial Vision Challenge aims to improve machine vision models.
problem Improving robustness of machine vision models and adversarial attacks.
method Organized a competition to measure progress in adversarial machine vision.
result Facilitated measurable progress in adversarial machine vision.
Symposium on making machine learning models more understandable.
problem Making machine learning models more understandable.
method Not specified in the abstract.
result Not specified in the abstract.
NIPS 2016 analyzed its review process to improve future conferences.
problem Growth in submissions, reviewers, and attendees requires better quality assessment.
method Analyzed data from the review process, including ordinal rankings experiments.
result Investigated the efficacy of collecting ordinal rankings from reviewers.
This is the Proceedings of NIPS 2016 Workshop on Interpretable Machine Learning for Complex Systems, held in Barcelona, Spain on December 9, 2016
Paper presents a multi-view ensemble model for classifying clinically actionable genetic mutations.
problem Classifying clinically actionable genetic mutations from text evidence.
method Developed a multi-view machine learning framework with ensemble classification models.
result Submitted an ensemble of nine basic gradient boosting models achieving top performance in NIPS 2017 Competition Track IV.
Google Brain competition on adversarial attacks and defenses.
problem Developing methods to generate and defend against adversarial examples.
method Organized a competition to encourage new adversarial attack and defense methods.
result Several top teams developed innovative methods in adversarial attacks and defenses.
Optimizes batch size in gradient descent for better accuracy and efficiency.
problem Determining optimal batch size in gradient descent methods.
method Optimizes batch size by balancing gradient estimate accuracy and sample cost.
result Empirically shows improved performance compared to existing methods.
The problem of Hybrid Linear Modeling (HLM) is to model and segment data using a mixture of affine subspaces. Different strategies have been proposed to solve this problem, however, rigorous analysis justifying their performance is missing. This paper suggests the Theoretical Spectral Curvature Clustering (TSCC) algori…
Unified dynamic approach for sparse model selection improves efficiency and accuracy.
problem Sparse model selection challenges in various fields.
method Iterative regularization path using Mirror Descent or Linearized Bregman Iterations.
result Path consistency theory with no false positives and minimax optimal error rate.
CSTEM models document topics using VAE with semantic distance.
problem Inability of previous topic models to explain semantic relations correctly.
method Continuous semantic topic embedding model using variational autoencoder and Mahalanobis distance.
result Improves topic coherence and semantic relation explanation.
Proposes HOPF framework for CC using higher-order propagation.
problem Collective Classification struggles with node information morphing across multiple hops.
method Iterative inference mechanism with differentiable kernels for multi-hop neighborhood information.
result NIP models preserve node information and provide more robust performance.
Improved guarantees for sparse random embeddings with explicit bounds and empirical superiority.
problem Improving the explicitness and sharpness of guarantees for sparse random embeddings.
method Explicit bounds, tighter estimates for quadratic chaos, extreme properties of sparse linear forms, and improved bounds for sums of independent random variables.
result Significantly outperforms prior works on various real-world datasets.
New research shows many recent defenses against adversarial examples are ineffective against black-box attacks.
problem The robustness of recent defenses against adversarial examples is insufficient, especially against black-box attacks.
method Evaluation of nine defenses on two black-box adversarial models and six attacks on CIFAR-10 and Fashion-MNIST datasets.
result Most recent defenses provide only marginal improvements in security () compared to undefended networks.
New algorithm finds optimal policy with polynomial trajectories in deterministic systems.
problem Finding optimal policy in deterministic systems with function approximation.
method Novel recursion-based algorithm with tight bounds on error and sample complexity.
result Optimal policy found using trajectories with $δ= O\left(ρ/\sqrt{\dim_E}
ight)$.
Boosts adversarial attacks with momentum to improve model robustness.
problem Vulnerability of deep neural networks to adversarial examples.
method Momentum-based iterative algorithms to boost adversarial attacks.
result More transferable adversarial examples and higher success rates for black-box attacks.
Study no-arbitrage conditions in 1D diffusion markets with interest rates.
problem Determining no-arbitrage conditions in 1D diffusion markets with interest rates.
method Established deterministic criteria for no-arbitrage notions in terms of scale function and speed measure.
result Revealed various effects, e.g., NIP not excluded by reflecting boundaries.
Neural Index Policy for multi-action bandits with heterogeneous budgets.
problem Real-world settings often involve multiple interventions with heterogeneous costs and constraints, breaking classical assumptions.
method Introduces a Neural Index Policy (NIP) that learns to assign budget-aware indices to arm-action pairs using a neural network and differentiable knapsack layer.
result Empirically achieves near-optimal performance while strictly enforcing heterogeneous budgets and scaling to hundreds of arms.
Enhances adversarial examples' transferability through diverse input patterns.
problem Low success rates of adversarial attacks in the black-box setting.
method Applying random transformations to input images at each iteration.
result Generates adversarial examples that transfer better to different networks.
99% of papers use real-world data, but only 3% provide formal comparisons.
problem Lack of complete argumentative chains in demonstrating algorithmic effectiveness in machine learning papers.
method Systematic review of NeurIPS papers from 2017, assessing completeness of argumentative steps.
result Only 3% of papers provide formal comparisons, indicating incomplete argumentative chains.
Stein variational Newton method accelerates SVGD for faster inference.
problem Efficient nonparametric variational inference.
method Accelerates SVGD by incorporating second-order information and optimal kernel selection.
result Significant computational gains over original SVGD in multiple test cases.
New fairness criterion aims to reduce financial harm to certain groups.
problem Financial decisions can disproportionately harm certain groups.
method Introduces 'equalized financial impact' to address fairness in financial decisions.
result Reduces financial harm to certain groups in financial decisions.
A new model CDTM improves text classification by concentrating document topics.
problem Unsupervised text classification with diverse topic distributions.
method Imposes an exponential entropy penalty on document topic distribution to encourage concentration.
result More coherent topics and concentrated, sparse document-topic distributions.
Nonnegative matrix factorization (NMF) has become a very popular technique in machine learning because it automatically extracts meaningful features through a sparse and part-based representation. However, NMF has the drawback of being highly ill-posed, that is, there typically exist many different but equivalent facto…
New algorithm approximates optimal transport cost with additive error in near-linear time.
problem Scalable approximation of optimal transport cost with additive error.
method Adapted classical graph algorithm of Gabow and Tarjan, with novel analysis.
result Achieves execution time of $O( rac{n^2 C}{δ} + rac{nC^2}{δ^2})$.
Random Gaussian noise and pixel discretization improve image classifier robustness.
problem Whitebox adversarial attacks decrease classifier accuracy.
method Inject random Gaussian noise, discretize pixels, and use any classifier.
result Reduces KL divergence and lower bound on classifier accuracy.
Robustness Analysis of Hottopixx, a Linear Programming Model for Factoring Nonnegative Matricesstat.ML
Although nonnegative matrix factorization (NMF) is NP-hard in general, it has been shown very recently that it is tractable under the assumption that the input nonnegative data matrix is close to being separable (separability requires that all columns of the input matrix belongs to the cone spanned by a small subset of…
This volume is a collection of contributions from the 5th Workshop on Machine Learning and Interpretation in Neuroimaging (MLINI) at the Neural Information Processing Systems (NIPS 2015) conference. Modern multivariate statistical methods developed in the rapidly growing field of machine learning are being increasingly…
We present the Wright-Fisher Indian buffet process (WF-IBP), a probabilistic model for time-dependent data assumed to have been generated by an unknown number of latent features. This model is suitable as a prior in Bayesian nonparametric feature allocation models in which the features underlying the observed data exhi…
We study Principal Component Analysis (PCA) in a setting where a part of the corrupting noise is data-dependent and, as a result, the noise and the true data are correlated. Under a bounded-ness assumption on the true data and the noise, and a simple assumption on data-noise correlation, we obtain a nearly optimal samp…
Study of particle system for sampling from probability densities.
problem Sampling from probability densities with unknown normalization.
method Interacting particle system and non-local nonlinear PDE.
result Empirical measure converges to solution of PDE.
Study tackles discretization problem in crafting adversarial examples for discrete integer domains.
problem Discretization problem in crafting adversarial examples for discrete integer domains.
method Proposes a black-box method to reduce adversarial example searching to a derivative-free optimization problem.
result Significantly higher success rate in crafting adversarial images in discrete integer domain compared to black-box methods.
Exclusive Topic Modelingstat.ML
ETM identifies field-specific keywords in text classification.
problem Unsupervised text classification with field-specific keywords.
method Weighted Lasso penalty and pairwise Kullback-Leibler divergence penalty for topic separation.
result ETM improves topic coherence by 22% and 10% compared to LDA.
Deep reinforcement learning models improve musculoskeletal running speed.
problem Optimizing a musculoskeletal model to run as fast as possible through an obstacle course.
method Deep reinforcement learning approaches, including DDPG, PPO, and TRPO, with modifications.
result Various modifications to known algorithms improve running performance.
We introduce the author-topic model, a generative model for documents that extends Latent Dirichlet Allocation (LDA; Blei, Ng, & Jordan, 2003) to include authorship information. Each author is associated with a multinomial distribution over topics and each topic is associated with a multinomial distribution over words.…
This paper improves coreset size via smoothed analysis.
problem Efficiently computing small subsets that approximate query errors.
method Smoothed analysis for approximate average error over queries.
result Deterministic and randomized algorithms for smaller coresets.
Nonnegative matrix factorization (NMF) has been shown recently to be tractable under the separability assumption, under which all the columns of the input data matrix belong to the convex cone generated by only a few of these columns. Bittorf, Recht, Ré and Tropp (`Factoring nonnegative matrices with linear programs', …
Topic models have proven to be a useful tool for discovering latent structures in document collections. However, most document collections often come as temporal streams and thus several aspects of the latent structure such as the number of topics, the topics' distribution and popularity are time-evolving. Several mode…
Lecture notes on kernel functions and Random Fourier Features.
problem Understanding and approximating kernel functions in machine learning.
method Mathematical background and proofs of concentration results.
result Estimation of error in Random Fourier Features approximation.
Variational inference improves neural network matrix factorization for stochastic blockmodels.
problem Improving predictive performance of neural network matrix factorization for stochastic blockmodels.
method Construct Bayesian neural networks and fit with variational inference.
result Variational inference can achieve equivalent performance to neural networks on Movielens data.
SAN replaces global pooling layers, improving accuracy and reducing overfitting.
problem Improving accuracy and reducing overfitting in deep neural networks.
method Introducing Set Aggregation Network (SAN) as a trainable global pooling layer.
result SAN improves classification accuracy and is less prone to overfitting.
We formulate a principle for classification with the knowledge of the marginal distribution over the data points (unlabeled data). The principle is cast in terms of Tikhonov style regularization where the regularization penalty articulates the way in which the marginal density should constrain otherwise unrestricted co…
Many popular network models rely on the assumption of (vertex) exchangeability, in which the distribution of the graph is invariant to relabelings of the vertices. However, the Aldous-Hoover theorem guarantees that these graphs are dense or empty with probability one, whereas many real-world graphs are sparse. We prese…
In the context of clustering, we assume a generative model where each cluster is the result of sampling points in the neighborhood of an embedded smooth surface; the sample may be contaminated with outliers, which are modeled as points sampled in space away from the clusters. We consider a prototype for a higher-order …
Topic modeling, a method for extracting the underlying themes from a collection of documents, is an increasingly important component of the design of intelligent systems enabling the sense-making of highly dynamic and diverse streams of text data. Traditional methods such as Dynamic Topic Modeling (DTM) do not lend the…
We consider the problem of object recognition with a large number of classes. In order to overcome the low amount of labeled examples available in this setting, we introduce a new feature learning and extraction procedure based on a factor model we call spike-and-slab sparse coding (S3C). Prior work on S3C has not prio…
We consider the problem of using a factor model we call {\em spike-and-slab sparse coding} (S3C) to learn features for a classification task. The S3C model resembles both the spike-and-slab RBM and sparse coding. Since exact inference in this model is intractable, we derive a structured variational inference procedure …
Local explanations of DNNs are insensitive to parameter values.
problem Sensitivity of local explanations to DNN parameter values.
method Assessed sensitivity of local explanations to DNN parameter values.
result DNNs with randomly-initialized weights produce similar explanations to those with learned weights.