Geometric vector perceptrons improve protein structure learning.
problem Learning from protein structure with efficient and natural representations.
method Introducing geometric vector perceptrons to extend dense layers for Euclidean vectors, integrating geometric and relational reasoning.
result Improves model quality assessment and computational protein design over existing methods.
A new geometric perceptron model improves 3D shape classification.
problem Challenges in geometric tasks involving point clouds using machine learning.
method Introduces multilayer geometric perceptron (MLGP) with geometric neurons.
result MLGP outperforms vanilla MLP in 3D shape classification and noise resistance.
A new algorithm finds a separating hyperplane with fewer updates.
problem Finding a separating hyperplane with minimal updates.
method Optimistic Perceptron algorithm.
result The Optimistic Perceptron finds a separating hyperplane with no more than $ rac{1}{γ}$ updates.
A new scoring function improves ordinal regression by combining binary predictions.
problem Improving ordinal regression prediction accuracy.
method Introduces a cumulative sum scoring function to combine binary predictions.
result Simplified formulation and two online learning algorithms converge under rank separability condition.
WavPool improves deep neural networks with wavelet-based pooling.
problem Improving efficiency and performance of deep neural networks.
method Introducing WavPool, a wavelet-transform-based pooling layer.
result WavPool outperforms existing network architectures by 10% on CIFAR-10.
The paper explores deep learning through algebra and geometry, highlighting geometric structures and differential processes.
problem Understanding the geometric and algebraic foundations of deep learning.
method Investigates neural networks from perceptron to transformer, emphasizing geometric structures and differential processes.
result A coordinate-free formulation of backpropagation equations using canonical scalar products on matrix spaces.
Perceptrons have been known for a long time as a promising tool within the neural networks theory. The analytical treatment for a special class of perceptrons started in seminal work of Gardner \cite{Gar88}. Techniques initially employed to characterize perceptrons relied on a statistical mechanics approach. Many of su…
IllinoisSL is a Java library for learning structured prediction models. It supports structured Support Vector Machines and structured Perceptron. The library consists of a core learning module and several applications, which can be executed from command-lines. Documentation is provided to guide users. In Comparison to …
An appropriate choice of the activation function (like ReLU, sigmoid or swish) plays an important role in the performance of (deep) multilayer perceptrons (MLP) for classification and regression learning. Prototype-based classification learning methods like (generalized) learning vector quantization (GLVQ) are powerful…
The study finds dense clusters of solutions in a simple neural network model, providing bounds for their existence.
problem Exploring the existence of minimizers in a simple neural network model with binary weights.
method Formulating the learning problem as a constraint satisfaction problem and computing moment bounds for the existence of solutions.
result First rigorous steps toward proving the existence of dense clusters of solutions in certain parameter regimes.
Paper proposes online algorithms for multiclass classification with partial labels.
problem Classifying data with partial labels.
method Avg Perceptron, Max Perceptron, Avg Pegasos, Max Pegasos algorithms.
result Mistake bounds for Avg Perceptron and regret bound for Avg Pegasos.
This paper proposes an improved design of the perceptron unit to mitigate the vanishing gradient problem. This nuisance appears when training deep multilayer perceptron networks with bounded activation functions. The new neuron design, named auto-rotating perceptron (ARP), has a mechanism to ensure that the node always…
We comment on the fact that gradient ascent for logistic regression has a connection with the perceptron learning algorithm. Logistic learning is the "soft" variant of perceptron learning.
Like most learning algorithms, the multilayer perceptrons (MLP) is designed to learn a vector of parameters from data. However, in certain scenarios we are interested in learning structured parameters (predictions) in the form of symmetric positive definite matrices. Here, we introduce a variant of the MLP, referred to…
We study and provide exposition to several phenomena that are related to the perceptron's compression. One theme concerns modifications of the perceptron algorithm that yield better guarantees on the margin of the hyperplane it outputs. These modifications can be useful in training neural networks as well, and we demon…
A note proves the binary perceptron's capacity is less than 0.847.
problem Determining the capacity of the binary perceptron.
method Conditional first moment method combined with known results on the spherical perceptron.
result Proves the binary perceptron's capacity is less than 0.847.
New method reduces deep learning training costs by approximating vector-jacobian products.
problem Efficiently training deep neural networks with reduced computational and memory costs.
method Randomized, unbiased approximations of vector-jacobian products during backpropagation.
result Validated potential for reducing deep learning training costs through unbiased estimates.
Quantum algorithms improve perceptron learning efficiency.
problem Improving quantum algorithms for perceptron learning.
method Revisiting and correcting a flawed quantum version space perceptron algorithm, proposing quantum-enhanced cutting-plane algorithms.
result Improved complexity bounds for quantum perceptron learning.
Efficient algorithms find solutions in a rare well-connected cluster at low constraint densities.
problem Finding solutions in the symmetric binary perceptron at low density.
method Formal proof of existence of a subdominant connected cluster and application of an efficient multiscale majority algorithm.
result An efficient algorithm can find solutions in a subdominant connected cluster with high probability.
Bayesian Perceptron offers fully Bayesian neural networks without complex computations.
problem Lack of uncertainty quantification in neural networks.
method Bayesian inference framework for perceptron training and predictions in closed-form.
result Analytical expressions for perceptron's output and weight learning provided.
Perceptron is a classic online algorithm for learning a classification function. In this paper, we provide a novel extension of the perceptron algorithm to the learning to rank problem in information retrieval. We consider popular listwise performance measures such as Normalized Discounted Cumulative Gain (NDCG) and Av…
Perceptrons are neuronal devices capable of fully discriminating linearly separable classes. Although straightforward to implement and train, their applicability is usually hindered by non-trivial requirements imposed by real-world classification problems. Therefore, several approaches, such as kernel perceptrons, have…
We demonstrate how quantum computation can provide non-trivial improvements in the computational and statistical complexity of the perceptron model. We develop two quantum algorithms for perceptron learning. The first algorithm exploits quantum information processing to determine a separating hyperplane using a number …
Proposes graph neural network layers for manifold-valued graphs.
problem Graphs with features in a Riemannian manifold.
method Diffusion layer and tangent multilayer perceptron.
result Outperforms state-of-the-art networks on Alzheimer's classification.
Binary perceptron's instability linked to replica symmetry breaking.
problem Understanding the relationship between algorithmic instability and replica symmetry breaking in binary perceptron learning.
method Established the connection between algorithmic instability and replica symmetry breaking by comparing the instability condition around the fixed point to the instability for breaking the replica symmetric solution of the free energy function.
result The instability condition around the algorithmic fixed point is identical to the instability for breaking the replica symmetric saddle point solution of the free energy function.
Linear classifiers in product space forms improve scRNA-seq data classification.
problem Linear classification in products of Euclidean, spherical, and hyperbolic spaces.
method Novel formulations of linear classifiers on Riemannian manifolds, proving expressive power, and formalizing perceptron and SVM classifiers.
result Linear classifiers in product space forms have the same expressive power as in Euclidean space of the same dimension.
We propose a new type of hidden layer for a multilayer perceptron, and demonstrate that it obtains the best reported performance for an MLP on the MNIST dataset.
Unified framework for accelerated Perceptron and related problems.
problem Finding optimal linear threshold functions for classification.
method Modern acceleration techniques, specifically optimistic online learning.
result Improved convergence rates for various Perceptron-related problems.
This paper connects ultrametric overlap gap properties to parametric RDT for symmetric binary perceptrons.
problem Characterizing statistical computational gaps in symmetric binary perceptrons.
method Developed an analytical union-bounding program to rigorously upper-bound constraint densities of ultrametric overlap gap properties.
result Obtained tightest bounds at the first two levels of ultrametric overlap gap properties, closely approaching parametric RDT estimates.
GD-VAEs learn dynamics from observations using geometric and topological information.
problem Learning parsimonious representations of nonlinear dynamics from observations.
method Develops data-driven methods incorporating geometric and topological information using Variational Autoencoders (VAEs).
result GD-VAEs provide methods for learning reduced dimensional representations of nonlinear dynamics.
We present a confidence-based single-layer feed-forward learning algorithm SPIRAL (Spike Regularized Adaptive Learning) relying on an encoding of activation spikes. We adaptively update a weight vector relying on confidence estimates and activation offsets relative to previous activity. We regularize updates proportion…
Study binary perceptrons' capacity using random duality theory.
problem Characterize the capacity of binary perceptrons with general thresholds.
method Utilized fully lifted random duality theory (fl RDT) to characterize the capacity.
result Characterizations match replica symmetry breaking predictions and uncover the capacity for zero-threshold scenario.
We study the computational capacity of a model neuron, the Tempotron, which classifies sequences of spikes by linear-threshold operations. We use statistical mechanics and extreme value theory to derive the capacity of the system in random classification tasks. In contrast to its static analog, the Perceptron, the Temp…
The study improves the perceptron's storage capacity by optimizing variable selection.
problem Distinguishing genuine structure from random correlations in high-dimensional data.
method Replica method from statistical mechanics for optimal variable selection.
result Optimal variable selection can surpass the Cover--Gardner bound for pattern classification.
Modified Perceptron handles strategic agents with limited position changes.
problem Learning linear classifiers in the presence of strategic agents that can manipulate their positions.
method Developed a modified Perceptron algorithm with bounded mistakes under various manipulation costs.
result The modified Perceptron achieves bounded mistakes even when manipulation costs are unknown.
Study analyzes learning dynamics in nonlinear perceptrons using stochastic-process approach.
problem Understanding the roles of nonlinearity and input-data distribution in neural network learning.
method Stochastic-process approach to derive flow equations for learning dynamics in nonlinear perceptrons.
result Input-data noise affects learning speed differently under supervised and reinforcement learning.
Transformers can scale both context and task, but MLPs can only scale task.
problem Understanding and scaling In-Context Learning in transformers.
method Simplified transformer architecture, feature map, and MLP combination.
result Simplified transformer can perform ICL and context-scaling but not task-scaling.
The study analyzes multi-class teacher-student perceptron performance and generalization errors.
problem Analyzing multi-class classification with the teacher-student perceptron.
method Deriving asymptotic expressions for Bayes-optimal and empirical risk minimization (ERM) generalization errors.
result Regularised cross-entropy minimization yields close-to-optimal accuracy for multi-class classification.
Classification is the most important process in data analysis. However, due to the inherent non-convex and non-smooth structure of the zero-one loss function of the classification model, various convex surrogate loss functions such as hinge loss, squared hinge loss, logistic loss, and exponential loss are introduced. T…
The paper analyzes phase transitions in transfer learning for perceptrons.
problem Understanding when transfer learning from a source task to a target task is beneficial.
method Theoretical analysis of a pair of related perceptron learning tasks.
result Reveals a phase transition from negative to positive transfer as task similarity changes.
Hypernetworks are neural networks that generate weights for another neural network. We formulate the hypernetwork training objective as a compromise between accuracy and diversity, where the diversity takes into account trivial symmetry transformations of the target network. We explain how this simple formulation gener…
New f-vectors reveal geometric Lefschetz-like decompositions of flag spheres.
problem Understanding f-vectors of balanced simplicial complexes and flag spheres. method Analyzing h-vectors and f-vectors of flag spheres and balanced simplicial complexes. result Found f-vectors leading to geometric Lefschetz-like decompositions. It has been known for a long time that the classical spherical perceptrons can be used as storage memories. Seminal work of Gardner, \cite{Gar88}, started an analytical study of perceptrons storage abilities. Many of the Gardner's predictions obtained through statistical mechanics tools have been rigorously justified. …
A new method separates data points using entropy minimization over a hypercube.
problem Classifying data points with linear or non-linear decision boundaries.
method Minimizing entropy over a hypercube to find separating parameters.
result Efficient and versatile for linear and non-linear separability.
Estimates small eigenvalues for geometrically finite manifolds.
problem Estimating small eigenvalues of Schrödinger operators.
method Geometrically finite manifolds, Riemannian vector bundles.
result Estimates the number of small eigenvalues.
The paper analyzes a simple neural network model with algebraic methods.
problem Finding minima of a ridge-regularized mean squared error for ReLU perceptrons.
method Developed a Divide-Enumerate-Merge strategy using computational algebra.
result Identifies both isolated and connected minima of the RR-MSE.
New bounds on neural network capacity for treelike sign perceptrons using RDT.
problem Determining the capacity of treelike sign perceptrons neural networks.
method Random Duality Theory (RDT) to establish upper bounds.
result Mathematically rigorous bounds on network capacity for any number of neurons.
Study shows perceptrons with random labels perform similarly to Gaussian data.
problem The assumption of Gaussian input data is often seen as a limitation in machine learning.
method Analyzed generalized linear classification (perceptron model) with random labels.
result Minimum training loss is independent of data covariance for high-dimensional input data.