Explores tensor products in hyperdimensional computing.
problem Understanding tensor products in hyperdimensional computing.
method Generalized results from graph embeddings to vector symbolic architectures and hyperdimensional computing.
result Tensor product is the most general and expressive representation with errorless unbinding and detection.
Paper introduces Laplace-HDC for better binary hyperdimensional computing.
problem Improving binary hyperdimensional computing for spatial information.
method Develops Laplace-HDC using the Laplace kernel and Haar convolutional features.
result Laplace-HDC outperforms previous methods in encoding spatial information.
Paper presents privacy-preserving techniques for HD computing.
problem Privacy loss in HD computing due to reversible computation.
method Quantization and pruning of hypervectors for differential privacy.
result Differentially private HD model for cloud inference.
FedHDPrivacy uses DP to improve FL in IoT, maintaining high accuracy.
problem Privacy threats in FL, especially in IoT environments.
method Integrates DP with neuro-symbolic computing, actively monitoring and adjusting noise.
result Maintains high performance in manufacturing monitoring, surpassing other FL methods.
ConformalHDC improves HDC's uncertainty quantification for neuromorphic learning.
problem Lack of rigorous uncertainty quantification in Hyperdimensional Computing.
method Combines conformal prediction with HDC's efficiency, proposing set-valued and point-valued formulations.
result Demonstrates improved robustness and accuracy in decoding neural stimulus information.
Simplified non-contrastive learning avoids representation collapse.
problem Training failure modes in self-supervised learning.
method Hyperdimensional computing and inductive bias.
result The approach avoids representation collapses.
G-Net constructs binary neural networks with high accuracy using randomized binary embeddings.
problem Creating high-accuracy binary neural networks with theoretical guarantees.
method Proposes a novel floating-point G-Net family with randomized binary embeddings and theoretical accuracy guarantees.
result Empirically, G-Net achieves almost 30% higher accuracy on CIFAR-10 compared to prior HDC models.
SynergicLearning combines NN and HD models for high accuracy and efficiency.
problem Combining neural networks and hyperdimensional learning for improved accuracy and efficiency.
method Hybrid model combining NN feature extraction and HD classification, parameterized hardware implementation.
result Improves accuracy by at least 10% compared to HD learning models and 1.60x power efficiency.
This paper presents an efficient binarized algorithm for both learning and classification of human epileptic seizures from intracranial electroencephalography (iEEG). The algorithm combines local binary patterns with brain-inspired hyperdimensional computing to enable end-to-end learning and inference with binary opera…
Proposes a new graph representation method using tensor products.
problem Dynamic graph representation and theoretical properties.
method Bind-and-sum approach in hyperdimensional computing (HDC), tensor product as binding operation.
result Memory vs. size analysis of graph representation size scaling.
A fast model estimates future prices from orderbook data.
problem Estimating future prices from orderbook data.
method Hyperdimensional vector Tsetlin machine framework for fast estimation.
result Demonstrated robust estimate of future prices.
Machine Learning algorithms based on Brain-inspired Hyperdimensional(HD) computing imitate cognition by exploiting statistical properties of high-dimensional vector spaces. It is a promising solution for achieving high energy efficiency in different machine learning tasks, such as classification, semi-supervised learni…
The deployment of machine learning algorithms on resource-constrained edge devices is an important challenge from both theoretical and applied points of view. In this article, we focus on resource-efficient randomly connected neural networks known as Random Vector Functional Link (RVFL) networks since their simple desi…
The paper proposes new cross-correlators using Price's Theorem and piecewise-linear decomposition.
problem Optimal method for estimating cross-correlations using finite samples.
method General mathematical framework using Price's Theorem and piecewise-linear decomposition.
result Some cross-correlators based on Huber's loss functions, MP functions, and LSE functions have higher SNR.
Recently, the deep learning community has given growing attention to neural architectures engineered to learn problems in relational domains. Convolutional Neural Networks employ parameter sharing over the image domain, tying the weights of neural connections on a grid topology and thus enforcing the learning of a numb…
Quantum computing speeds up multi-period asset allocation.
problem High computational complexity in classic computing for multi-period asset allocation.
method Applied quantum computing to simulate multi-asset portfolio using historic data.
result Quantum computing offers significant advantages over classical computing in finance.
The paper analyzes the pricing of a new compute futures asset.
problem Uncertainty in AI adoption and pricing of compute capital.
method An asset-pricing framework for compute futures, including synthetic futures pricing.
result Preliminary evidence suggests a positive compute risk premium.
Quantum computing offers energy savings over classical computing.
problem Energy efficiency in computing services.
method Cournot competition model constrained by energy usage.
result Quantum computing firms can outperform classical counterparts in energy efficiency.
The paper introduces reservoir computing models for complex systems.
problem Modeling complex engineering systems using nonlinear autoregression.
method Introduces reservoir computing with output feedback as stationary and ergodic infinite-order nonlinear autoregressive models.
result Demonstrates versatility of classical and quantum reservoir computers in modeling synthetic and real data.
This work makes neural sequence models more efficient by controlling computation.
problem Fixed compute for all examples in neural networks.
method Conditional computation to adapt compute to example complexity.
result Conditional Computation Transformer (CCT) improves efficiency and performance.
Defines computable learning for binary classification over metric spaces.
problem Defines computable PAC learning for binary classification over computable metric spaces.
method Provides sufficient conditions for ERM learners to be computable and bounds the strong Weihrauch degree of an ERM learner.
result Gives a hypothesis class that does not admit any proper computable PAC learner with computable sample function.
Automatic computation speeds up crosscap number calculation for alternating knots.
problem Computing crosscap numbers for alternating knots efficiently.
method Introduced an automatic computation with complexity O(E3). result Crosscap numbers of alternating knots can be computed in O(E3) time. TKFT models computation via smooth vector fields, simulating functions in a single dynamical step.
problem Modeling computation in a single step.
method Established Topological Kleene Field Theory (TKFT) as a new model of computation.
result Any computable function can be simulated in a single go of a dynamical system.
Stochastic reservoir computing is shown to be a universal approximator.
problem Theoretical justification for using stochastic reservoirs in machine learning.
method Investigated stochastic reservoir computing using probabilities of reservoir states as readout.
result Stochastic reservoir computers are universal approximating classes.
Machine learning impacts computational math, offering new functions approximations.
problem Machine learning's black box nature hinders further progress in computational math.
method Analyzes machine learning's impact on computational math and vice versa.
result Integrating computational math with machine learning can enhance both fields.
Coded computation techniques provide robustness against straggling servers in distributed computing, with the following limitations: First, they increase decoding complexity. Second, they ignore computations carried out by straggling servers; and they are typically designed to recover the full gradient, and thus, canno…
Method for computing Khovanov homology of tangles.
problem Limited explicit computational studies of Khovanov homology for tangles.
method Arc reduction approach to compute Khovanov homology.
result Derived and computed Poincaré polynomials for simple and complex tangles.
With the rapid growth of the data volume and the fast increasing of the computational model complexity in the scenario of cloud computing, it becomes an important topic that how to handle users' requests by scheduling computational jobs and assigning the resources in data center. In order to have a better perception of…
This paper simplifies computing higher-order U-statistics efficiently.
problem The inefficiency of computing higher-order U-statistics in practice. method Decomposition, connection to Einstein summation, and treewidth-based complexity estimate.
result A new, more efficient algorithm to compute U-statistics. Survey on computational models in dynamical systems, including new universality concepts.
problem Understanding the relationship between computational models and dynamical systems.
method Review of recent works on Turing universality, Topological Kleene Field Theories, and dynamical bordisms.
result Introduction of new perspectives on computability through dynamical systems.
Computations for prime knots up to 11 crossings.
problem Computing HOMFLY homology for prime knots.
method Direct computations for all prime knots up to 11 crossings.
result HOMFLY homology determined for all prime knots up to 11 crossings.
Survey on quantum computing and neural networks.
problem Understanding and comparing quantum computing and neural networks.
method Introduction to quantum computing concepts, explanation of quantum computing paradigms, and analysis of quantum neural networks.
result Current state-of-the-art in quantum neural networks.
New methods improve Reservoir Computing for chaotic time series prediction.
problem Chaotic time series prediction in Reservoir Computing.
method Established Recurrent Kernel limit, introduced Structured Reservoir Computing.
result Structured Reservoir Computing is faster and more memory-efficient.
Quantum computing promises faster bioinformatics, but challenges remain.
problem Efficient bioinformatics processing and drug discovery.
method Quantum algorithms for optimization, simulation, and machine learning.
result Quantum computing can significantly speed up bioinformatics tasks.
We present two paradigms relating algebraic, topological and quantum computational statistics for the topological model for quantum computation. In particular we suggest correspondences between the computational power of topological quantum computers, computational complexity of link invariants and images of braid grou…
As inductive inference and machine learning methods in computer science see continued success, researchers are aiming to describe ever more complex probabilistic models and inference algorithms. It is natural to ask whether there is a universal computational procedure for probabilistic inference. We investigate the com…
Quantum computing promises new financial modeling.
problem Traditional financial modeling limitations.
method Overview of quantum computing applications in finance.
result Quantum computing can enhance financial modeling.
We look into computational aspects of two classical knot invariants. We look for ways of simplifying the computation of the coloring invariant and of the Alexander module. We support our ideas with explicit computations on pretzel knots.
Study error bounds in evaluating distributional computational graphs.
problem Error analysis in evaluating graphs with inputs as probability distributions.
method Establish non-asymptotic error bounds using Wasserstein-1 distance.
result Non-asymptotic error bounds for discretization errors in distributional computational graphs.
Quantum computing techniques improve graph analysis and community detection.
problem Analyzing large graphs efficiently and accurately.
method Used quantum annealing and quantum gate computers for community detection and regularity checking.
result Demonstrated the effectiveness of quantum computing in solving complex graph problems.
New method speeds up knot computations in 3D.
problem Computational complexity in knot theory.
method 3D representation of knots for faster computation.
result Savings in computational complexity for knot invariants.
PALMS reconstructs large-scale networks efficiently with parallel computing.
problem Reconstructing large-scale latent networks from observed dynamics is computationally challenging.
method PALMS (Parallel Adaptive Lasso with Multi-directional Signals) framework for distributed network reconstruction.
result PALMS substantially reduces computational complexity and storage requirements.
This paper explores the interactions between knot theory and quantum computing. On one side, knot theory has been used to create models of quantum computing, and on the other, it is a source of computational problems. Knot theory is often used to introduce topological idea to people without a formal mathematical backgr…
Adaptive compute allocation improves model performance by prioritizing harder queries.
problem Inefficiency in allocating test-time compute uniformly across all queries.
method Formulated as a bandit learning problem, proposed adaptive algorithms that estimate query difficulty and allocate compute accordingly.
result Achieved up to 15.29% relative performance improvement on various benchmarks.
Quantum computing offers financial industry new optimization and risk management tools.
problem Traditional computing limits financial industry's problem-solving capabilities.
method Structured review of quantum computing platforms, algorithms, and use cases.
result Quantum computing can enhance financial industry applications like optimization and risk management.
Optimizes K inner simulations for least-square Monte Carlo to reduce computational cost.
problem Computing conditional expectation E[f (Y)|X] with limited samples.
method Determines optimal number of Y samples (K) for given computational budget.
result Computational gain is maximized when sampling Y given X is inexpensive.
QBC uses quantum computers to speed up Bayesian computation.
problem Exponential speed-up in Bayesian computation.
method Quantum von Neumann measurement for simulating ML algorithms.
result Quantum versions of regression, Gaussian processes, and SGD.
This work reduces computation cost for on-device CNN training.
problem High computation cost during on-device CNN training.
method Self-supervised instance filtering and error map pruning.
result Substantial computation saving without significant accuracy loss.