Study aerodynamics of flying saucers on curved spaces.
problem Understanding the motion of flying saucers on different types of curved surfaces.
method Identifying structures on the configuration space of flying saucers and relating them to the geometry of the underlying curved manifold.
result The symmetries of the flying saucer's motion can be described by the split form of the exceptional Lie algebra G2 when the manifold has a certain type of structure.
A flying saucer's flight is mathematically modeled with geometric structures.
problem Modeling the complex flight maneuvers of a flying saucer.
method Imposing nonlinear restrictions on the saucer's velocity to define geometric structures.
result Three types of flat parabolic geometries are defined for the saucer's configuration space.
Spinors help study unique five-dimensional contact structures.
problem Understanding unique five-dimensional contact structures.
method Using classical two-component spinors, define directional derivatives in contact directions.
result Calculate invariant torsion of G2 contact structure. 3D flying wings created for any angle asymptotic cones.
problem Creating 3D steady gradient Ricci solitons with any angle asymptotic cones.
method Constructing 3D flying wings for any angle asymptotic cones.
result 3D flying wings constructed for any angle asymptotic cones.
Researchers discover a new family of 3D solitons that are flying wings.
problem Verifying a conjecture about 3D steady gradient Ricci solitons.
method Analyzing a family of 3D flying wing solitons and proving properties of these solitons.
result 3D flying wing solitons are non-collapsed and have non-zero scalar curvature at infinity.
A new classifier encodes local neighborhoods for each class using Fly Bloom Filters.
problem Efficiently classify data with single-pass learning.
method Proposes a new classifier that encodes local neighborhoods for each class with per-class Fly Bloom Filters.
result The proposed classifier's performance is competitive with nearest-neighbor classifiers and other single-pass classifiers.
Classi-Fly uses machine learning to infer aircraft categories from open data.
problem Lack of metadata for aircraft in open data sources.
method Machine learning approach based on aircraft movement patterns.
result Correct aircraft category inference with over 88% accuracy.
Fruit fly brain network learns word embeddings using sparse binary codes.
problem Learning semantic word representations from text.
method Inspired by mushroom body neural network, sparse binary hash codes.
result Fruit fly network achieves comparable NLP performance with reduced resources.
The densification of small-cell base stations in a 5G architecture is a promising approach to enhance the coverage area and facilitate the ever increasing capacity demand of end users. However, the bottleneck is an intelligent management of a backhaul/fronthaul network for these small-cell base stations. This involves …
3D steady gradient Ricci solitons are all O(2)-symmetric.
problem Characterizing 3D steady gradient Ricci solitons.
method Analyzing asymptotic behavior and using O(2) symmetry.
result All 3D steady gradient Ricci solitons are O(2)-symmetric.
ADVISOR dynamically balances imitation and reinforcement learning to overcome the imitation gap.
problem The gap between imitation learning and reinforcement learning when teaching agents have privileged information.
method Adaptive Insubordination (ADVISOR) dynamically weights imitation and reward-based reinforcement learning losses.
result On-the-fly switching with ADVISOR outperforms pure imitation, pure reinforcement learning, and their combinations.
Proposes on-the-fly joint feature selection and classification for time-sensitive decisions.
problem Online feature selection and classification for time-sensitive decision making.
method Proposes a framework for joint feature selection and classification on-the-fly, optimizing feature usage and classification accuracy.
result Demonstrates superior performance over state-of-the-art methods on various datasets.
Adapts agent strategies on-the-fly for better cross-play in cooperative settings.
problem Cross-play issues between self-play agents and unseen partners.
method Adapts agent strategies using posterior belief updates via Gibbs sampling.
result Achieves strong cross-play in the Hanabi game without prior knowledge of partners' strategies.
APINNs use neural networks to solve MCMC problems efficiently.
problem Accurate Bayesian parameter estimation for systems governed by PDEs.
method Construct an offline PINN-UQ model and refine it on the fly using MCMC samples.
result Guaranteed approximation error less than a residual error threshold.
Dynamic neural network toolkits such as PyTorch, DyNet, and Chainer offer more flexibility for implementing models that cope with data of varying dimensions and structure, relative to toolkits that operate on statically declared computations (e.g., TensorFlow, CNTK, and Theano). However, existing toolkits - both static…
We introduce a method by which a generative model learning the joint distribution between actions and future states can be used to automatically infer a control scheme for any desired reward function, which may be altered on the fly without retraining the model. In this method, the problem of action selection is reduce…
Deep reinforcement learning controls drones without model knowledge.
problem Real-time robot control without engineered models.
method Learnt probabilistic model of drone dynamics, model-based reinforcement learning.
result Controller and value function optimized through generated latent trajectories.
New LSH algorithms improve nearest-neighbor search performance.
problem Efficiently searching for similar high-dimensional data.
method High-dimensional locality-sensitive hashing (LSH) based on fruit fly olfactory circuit.
result New LSH algorithms outperform existing methods on benchmark datasets.
Constructs new steady gradient Ricci solitons for higher dimensions.
problem Finding new steady gradient Ricci solitons with non-negative curvature.
method Constructing continuous families of Ricci flows from spherical polyhedra, proving stability.
result Produces new examples of steady gradient Ricci solitons for n≥4. Binary autoencoder with sparse hidden layer preserves information and zero reconstruction error.
problem Preserving information and zero reconstruction error in binary neural networks.
method Binary autoencoder with random binary weights, sparse hidden layer, and varying neuron thresholds.
result Zero reconstruction error for any input with a large hidden layer and varying neuron thresholds.
Framework detects anomalies in real-time PMU data.
problem Anomaly detection in power grid operations.
method Statistical learning and dynamical model.
result Effective anomaly detection and classification.
Metareasoning optimizes modular systems by dynamically adjusting configurations.
problem Maximizing system utility in high-stakes tasks with modular subsystems.
method Employing reinforcement learning with rich contextual representations to dynamically adjust module configurations.
result Significant improvement in system performance across various reinforcement learning techniques.
A new method for generating replay samples on the fly, optimizing for not forgetting.
problem Addressing the issue of forgetting in neural networks.
method Generates auxiliary samples on the fly using the model's implicit memory, specialized to each real training batch.
result Optimizing for not forgetting leads to more efficient and scalable generation of specialized samples.
It is challenging to handle a large volume of labels in multi-label learning. However, existing approaches explicitly or implicitly assume that all the labels in the learning process are given, which could be easily violated in changing environments. In this paper, we define and study streaming label learning (SLL), i.…
Automatically detects and down-weights noisy samples in machine learning training.
problem Numerical noise in reference data hampers the accuracy of machine learning models.
method On-the-fly outlier detection using exponential moving average to identify and down-weight noisy samples.
result The method prevents overfitting and matches the performance of iterative refinement with reduced overhead.
A simple baseline for extreme multi-label classification using random projections.
problem Automatically annotating data points with relevant labels from a large label vocabulary.
method On-the-fly global embedding using random projections, with an ensemble of learners.
result Competitive accuracy compared to existing methods, with significant speed-up and model-size reduction.
UAVs learn to collect data from IoT sensors efficiently.
problem Efficient UAV path planning for wireless data collection.
method Deep reinforcement learning (DDQN) with experience replay and convolutional layers.
result UAV control policy generalizes over changing scenario parameters.
New Kähler solitons found that are not U(n)-invariant.
problem Whether every steady gradient Kähler-Ricci soliton of positive curvature on Cn is U(n)-invariant. method Constructing a family of U(1)imesU(n−1)-invariant, but not U(n)-invariant, steady gradient Kähler-Ricci solitons. result Found a family of complete steady gradient Kähler-Ricci solitons with strictly positive curvature operator on Cn for n≥3. A novel algorithm optimizes sparsity in reservoir computing inspired by insect brain.
problem Optimizing sparsity in reservoir computing networks.
method Inspired by insect brain, the algorithm optimizes sparsity levels by adjusting node firing thresholds.
result The algorithm outperforms standard gradient descent on tasks involving better classification, memorization, and convergence.
The practical performance of online stochastic gradient descent algorithms is highly dependent on the chosen step size, which must be tediously hand-tuned in many applications. The same is true for more advanced variants of stochastic gradients, such as SAGA, SVRG, or AdaGrad. Here we propose to adapt the step size by …
We present a hybrid continuum-atomistic scheme which combines molecular dynamics (MD) simulations with on-the-fly machine learning techniques for the accurate and efficient prediction of multiscale fluidic systems. By using a Gaussian process as a surrogate model for the computationally expensive MD simulations, we use…
SON-NMF estimates nonnegative rank on-the-fly for NMF.
problem Estimating the nonnegative rank of data in NMF.
method Sum-of-norms (SON) regularization to reduce rank, combined with a first-order BCD algorithm.
result SON-NMF can automatically estimate the rank from data without prior knowledge.
We introduce two Python frameworks to train neural networks on large datasets: Blocks and Fuel. Blocks is based on Theano, a linear algebra compiler with CUDA-support. It facilitates the training of complex neural network models by providing parametrized Theano operations, attaching metadata to Theano's symbolic comput…
Resolves conjecture on cylindrical mean curvature flows in all dimensions.
problem Mean Convex Neighborhood Conjecture for cylindrical singularities.
method Complete classification of ancient, asymptotically cylindrical flows; refined asymptotic analysis; leading mode condition; induction over thresholds.
result Establishes mean-convex neighborhood for cylindrical singularities; provides local models and canonical families.
We describe a mechanism by which artificial neural networks can learn rapid adaptation - the ability to adapt on the fly, with little data, to new tasks - that we call conditionally shifted neurons. We apply this mechanism in the framework of metalearning, where the aim is to replicate some of the flexibility of human …
When confronted with massive data streams, summarizing data with dimension reduction methods such as PCA raises theoretical and algorithmic pitfalls. Principal curves act as a nonlinear generalization of PCA and the present paper proposes a novel algorithm to automatically and sequentially learn principal curves from d…
New method finds best neural architecture during learning.
problem Active learning of deep neural networks with known architectures.
method Neural architecture search during active learning.
result Outperforms fixed architecture active learning.
New methods reduce private federated learning communication automatically.
problem Reducing communication in private federated learning.
method Automatic compression rate adjustment based on training error, using secure aggregation and differential privacy.
result Provable instance-optimal for mean estimation, achieving favorable compression rates.
We present NAVREN-RL, an approach to NAVigate an unmanned aerial vehicle in an indoor Real ENvironment via end-to-end reinforcement learning RL. A suitable reward function is designed keeping in mind the cost and weight constraints for micro drone with minimum number of sensing modalities. Collection of small number of…
Derivative-informed models improve financial surrogates for accurate hedging and risk management.
problem Developing fast surrogate models for financial derivatives and risk quantities.
method Derivative-informed operator learning framework combining neural operators, random features, and tangent sensitivity equations.
result The framework reduces hedging and risk errors by 40-76% compared to standard surrogates.
Proposes a flexible normalization method to handle multi-modal data.
problem Reduced effectiveness of batch normalization in multi-modal distributions.
method Extends normalization to multiple means and variances, detecting data modes on-the-fly.
result Outperforms batch normalization and other methods in various experiments.
Efficiently learns loss functions for better model performance.
problem Finding an optimal loss function for model validation.
method Asymptotically optimal anytime algorithm in worst case, provably efficient in idealized case.
result Significantly faster than state-of-the-art alternatives for tuning loss function hyperparameters.
We consider the problem of learning convex aggregation of models, that is as good as the best convex aggregation, for the binary classification problem. Working in the stream based active learning setting, where the active learner has to make a decision on-the-fly, if it wants to query for the label of the point curren…
Math model helps bees decide between winter survival and raising young.
problem Deciding between winter survival and raising young bees in honeybee colonies.
method Mathematical model considering resource geometry around the hive.
result Optimal resource allocation strategy for honeybee colonies.
GrateTile optimizes CNN feature map storage for efficient data access.
problem Efficient storage and access of sparse CNN feature maps.
method Divides feature maps into uneven-sized subtensors, compresses and stores them in a compressed yet accessible format.
result Average 55% DRAM bandwidth reduction with minimal indexing overhead.
Safe reinforcement learning for robots using model predictive shielding.
problem Ensuring safety of learned policies in robotics tasks.
method Model Predictive Shielding (MPS) that switches between learned and backup policies.
result Guaranteed safety of learned policies in challenging robotics tasks.
Paper proves conjecture about star-shaped curves evolving under GAPF, but not always preserves star shape.
problem What conditions guarantee global existence of Gage's area-preserving flow for nonconvex initial curves?
method Using Dittberner's singularity analysis theory, constructed a ``flying wing'' curve to show limitations.
result Gage's area-preserving flow does not always preserve star-shapedness of evolving curves.
A reinforcement learning framework for Mars rover control using temporal logic.
problem Sparse rewards in continuous-state continuous-action MDPs with high-level temporal structures.
method Actor-critic, model-free, online RL framework with modular DDPG architecture.
result Success rate of synthesised policy in Mars rover experiment.