Survey on random features for kernel approximation, focusing on algorithms, theory, and practical applications.
problem Efficiently approximating kernel methods for large-scale problems.
method Random features techniques to speed up kernel methods.
result Need for a high number of random features for good approximation quality.
Abstracts index for ML4H workshop at NeurIPS 2019.
problem No specific problem stated; index of accepted abstracts.
method Not specified; index of accepted abstracts.
result No specific result stated.
This is the Proceedings of NeurIPS 2018 Workshop on Machine Learning for the Developing World: Achieving Sustainable Impact, held in Montreal, Canada on December 8, 2018
This volume represents the accepted submissions from the Machine Learning for Health (ML4H) workshop at the conference on Neural Information Processing Systems (NeurIPS) 2018, held on December 8, 2018 in Montreal, Canada.
Improved disentanglement in VAEs using aggregated feature maps.
problem Improving disentanglement in Variational Autoencoders (VAEs).
method Regionally aggregated feature maps extracted from pre-trained CNNs on ImageNet.
result 2nd place in NeurIPS 2019 disentanglement challenge.
New property ensures neural networks generalize well with limited data.
problem Limited training data limits model generalization in neural networks.
method Introduces NeuRIP, a uniform concentration event for ReLU networks.
result All shallow ReLU networks generalize uniformly if they achieve NeuRIP.
Replication confirms CGD's effectiveness in competitive games.
problem Reproducibility of a novel Nash equilibrium algorithm.
method Replicated experiments and provided Python implementation.
result CGD avoids oscillatory and divergent behaviours.
NeurIPS 2019 program improves reproducibility in machine learning.
problem Ensuring machine learning research results are reproducible and reliable.
method Code submission policy, reproducibility challenge, and checklist integration.
result Improved reproducibility standards across the machine learning community.
Squirrel switches between optimizers for better performance.
problem Finding the best optimizer for a given problem.
method Switches between different optimizers based on performance.
result Improves performance on various problems.
AI agents beat previous best on NetHack, but symbolic bots still outperform.
problem Developing AI agents that can ascend in the NetHack game.
method Used a procedurally generated NetHack Learning Environment for reinforcement learning.
result Symbolic bots outperform neural approaches on NetHack.
We organized a competition on Autonomous Lifelong Machine Learning with Drift that was part of the competition program of NeurIPS 2018. This data driven competition asked participants to develop computer programs capable of solving supervised learning problems where the i.i.d. assumption did not hold. Large data sets w…
NeurIPS 2020 competition seeks to predict deep learning generalization.
problem Understanding and predicting generalization in deep learning models.
method Propose complexity measures to accurately predict generalization performance.
result A robust complexity measure could improve deep learning reliability.
Researchers improved Minecraft game performance using imitation learning.
problem Achieving state-of-the-art performance in immersive environments like Minecraft.
method Applied imitation learning to Minecraft, optimizing network architecture, loss function, and data augmentation.
result Reported stronger results than previous experiments, reaching second place in a competition.
Improved disentanglement through learned feature aggregation.
problem Disentangling latent factors in images.
method Variational autoencoder trained on regionally aggregated feature maps from ImageNet.
result 2nd place in NeurIPS 2019 disentanglement challenge.
Study confirms improved performance of Self-Critique and Adapt method.
problem Improving performance of MAML++ method.
method Self-Critique and Adapt (SCA) method.
result SCA method improves performance of MAML++.
New adaptive attacks bypass many defenses to adversarial examples.
problem Adversarial example defenses are not adequately evaluated using adaptive attacks.
method Detailed analysis of thirteen defenses, demonstrating their vulnerabilities to adaptive attacks.
result Adversarial example defenses are more vulnerable to adaptive attacks than previously thought.
Quo Vadis team improves Traffic4cast competition with a seasonal bias model.
problem Improving performance of traffic flow prediction models.
method Temporal regression module with spatio-temporal biases.
result Mean squared error of 9.47×10⁻³ on test data.
This article reviews machine learning methods for behavioral sciences.
problem Applying machine learning to behavioral science data.
method Overview of classical and recent algorithms for tabular, behavioral, and textual data.
result Practical guidance for using machine learning in behavioral science.
Improved algorithm for contextual bandits with reduced regret.
problem Adversarial contextual bandits with i.i.d. contexts.
method Oracle-efficient relaxation with O(T32(Klog(∣Π∣))31) regret bound. result First to improve regret bound and match original bound for stochastic case.
Catalyst.RL accelerates RL research with efficient training.
problem Efficient reinforcement learning training in complex environments.
method Open-source PyTorch framework with distributed training and RL algorithms.
result Catalyst.RL achieved 2nd place in a computationally expensive RL challenge.
Objective: To determine the completeness of argumentative steps necessary to conclude effectiveness of an algorithm in a sample of current ML/AI supervised learning literature. Data Sources: Papers published in the Neural Information Processing Systems (NeurIPS, née NIPS) journal where the official record showed a 2017…
Bayesian optimization outperformed random search in machine learning hyperparameter tuning challenge.
problem Optimizing hyperparameters of machine learning models using derivative-free methods.
method Bayesian optimization vs. random search on real datasets.
result Bayesian optimization significantly outperformed random search in held-out objective functions.
New machine learning pipeline solves dynamic vehicle routing problems efficiently.
problem Efficiently handling same day deliveries in e-commerce logistics.
method Combination of machine learning and combinatorial optimization.
result Ranked first in the EURO Meets NeurIPS Vehicle Routing Competition.
New method accelerates Pommerman training with imitation and reinforcement learning.
problem Training complex multi-agent games like Pommerman.
method Imitation learning followed by PPO reinforcement learning with modifications.
result Significantly faster training compared to other methods.
Improved learning bounds for corrupted data using thresholded gradient descent.
problem Learning from corrupted data with adversarial noise.
method Thresholded gradient descent for sigmoidal, leaky-ReLU, and ReLU activations.
result Improved approximation bounds for various activation functions.
Causal inference uses observations to infer the causal structure of the data generating system. We study a class of functional models that we call Time Series Models with Independent Noise (TiMINo). These models require independent residual time series, whereas traditional methods like Granger causality exploit the var…
Challenge hides and seeks privacy in clinical time-series data.
problem De-identifying clinical time-series data while preserving utility and privacy.
method Synthetic data generation to preserve temporal dynamics and limit re-identification risk.
result A novel competition tracks synthetic data generation and patient re-identification.
Study shows simple vector quantization measures correlate with deep learning generalization.
problem Understanding and predicting generalization in deep learning models.
method Applying complexity measures from approximation and information theory to deep learning features.
result Simple vector quantization measures correlate well with generalization performance in deep learning.
Improved deep neural network generalization through noise resilience.
problem Understanding and predicting generalization error of deep neural networks.
method Noise resilience measures to predict generalization error.
result Secured 5th position in the PGDL competition at NeurIPS 2020.
In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, participants were tasked with building a controller for a musculoskeletal model with a goal of matching a given time-varying velocity vector. Top participants were invited to describe their algorithms. In this work, we describe the challenge and pre…
Extended LSTM improves language modeling performance.
problem Improving LSTM for large-scale language modeling.
method Exponential gating, modified memory structure, and residual stacking.
result xLSTM outperforms state-of-the-art models in performance and scaling.
Improved privacy-preserving methods for estimating multiple samples from distributions.
problem Estimating multiple samples from distributions while maintaining privacy.
method Developed new multi-sampling techniques for differentially private data estimation.
result Achieved significant reduction in sample complexity for multi-sampling from finite domains and Gaussian distributions.
Innovation is to organizations what evolution is to organisms: it is how organisations adapt to changes in the environment and improve. Governments, institutions and firms that innovate are more likely to prosper and stand the test of time; those that fail to do so fall behind their competitors and succumb to market an…
Improved reinforcement learning in Minecraft with human demonstrations.
problem Sample inefficiency in reinforcement learning.
method Training policy networks on human demonstrations first, then fine-tuning with reinforcement learning.
result Best agent achieved a mean score of 48 in Minecraft.
We study a multiplayer stochastic multi-armed bandit problem in which players cannot communicate, and if two or more players pull the same arm, a collision occurs and the involved players receive zero reward. We consider the challenging heterogeneous setting, in which different arms may have different means for differe…
New findings show limitations in converting private learning to online learning efficiently.
problem Limitations in converting private learning to online learning efficiently.
method Assuming one-way functions, we show an efficient conversion from pure-private learners to online learners is impossible.
result Efficient conversion from pure-private learners to online learners is impossible under certain assumptions.
New algorithm for privacy-preserving nonconvex optimization.
problem Privacy-preserving nonconvex empirical risk minimization.
method Differentially private stochastic gradient descent algorithm.
result Achieves strong privacy guarantees efficiently with improved utility.
MineRL Competition reduced reinforcement learning sample needs.
problem Sample inefficiency in reinforcement learning.
method Human demonstrations and imitation learning integrated into reinforcement learning algorithms.
result Top solutions used deep reinforcement learning and imitation learning.
We consider adversarial examples for image classification in the black-box decision-based setting. Here, an attacker cannot access confidence scores, but only the final label. Most attacks for this scenario are either unreliable or inefficient. Focusing on the latter, we show that a specific class of attacks, Boundary …
Disentanglement-PyTorch library facilitates disentangled representation learning.
problem Unsupervised learning of disentangled representations.
method Modular library for variational algorithms, decoupling architectures, latent space, and training algorithms.
result Achieved 3rd rank in NeurIPS 2019 Disentanglement Challenge.
Ringmaster ASGD improves Asynchronous SGD's efficiency under varying worker times.
problem Suboptimal performance of Asynchronous SGD under heterogeneous worker computation times.
method Ringmaster ASGD, a novel Asynchronous SGD method with optimal time complexity.
result Ringmaster ASGD achieves optimal time complexity under arbitrary worker heterogeneity.
Schedule-free SGD is optimal for nonconvex optimization problems.
problem Nonconvex optimization in neural networks.
method Developed a general framework for online-to-nonconvex conversion, which converts schedule-free SGD into an effective nonconvex optimization algorithm.
result Schedule-free SGD achieves optimal iteration complexity for nonsmooth, nonconvex optimization problems.
We identify a trade-off between robustness and accuracy that serves as a guiding principle in the design of defenses against adversarial examples. Although this problem has been widely studied empirically, much remains unknown concerning the theory underlying this trade-off. In this work, we decompose the prediction er…
In this paper we introduce a new approach to topic modelling that scales to large datasets by using a compact representation of the data and by leveraging the GPU architecture. In this approach, topics are learned directly from the co-occurrence data of the corpus. In particular, we introduce a novel mixture model whic…
Despite the recent progress in deep reinforcement learning field (RL), and, arguably because of it, a large body of work remains to be done in reproducing and carefully comparing different RL algorithms. We present catalyst.RL, an open source framework for RL research with a focus on reproducibility and flexibility. Ma…
Deep RL drone trained to compete against classical path planning in drone racing.
problem Optimizing long-term drone racing strategies using reinforcement learning.
method Used PPO algorithm on a simulated quadrotor in a racing environment created with AirSim.
result Deep RL agent outperformed classical path planning in drone racing competitions.
We derive generalization and excess risk bounds for neural nets using a family of complexity measures based on a multilevel relative entropy. The bounds are obtained by introducing the notion of generated hierarchical coverings of neural nets and by using the technique of chaining mutual information introduced in Asadi…
The paper explains how nearest neighbor methods succeed in prediction.
problem Explaining the success of nearest neighbor methods in prediction.
method The paper covers both theoretical and practical aspects of nearest neighbor methods, including statistical guarantees and practical algorithms.
result The paper provides nonasymptotic statistical guarantees and practical algorithms for nearest neighbor methods.