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.
We analyze anomaly detection class imbalance using a solvable model.
problem Class imbalance hampers anomaly detection performance.
method We use an exact solution of the teacher-student perceptron model through replica theory.
result Optimal train imbalance is often different from 50%, influenced by intrinsic imbalance and data abundance.
Study shows how much information can be learned from sparse signals with limited data.
problem Understanding information limits in learning sparse signals with sublinear data.
method Proved variational formula for mutual information, derived MMSE expressions, analyzed phase transitions.
result Nonincreasing piecewise constant MMSE with all-or-nothing phase transitions for certain conditions.
Optimal task order improves continual learning performance.
problem Challenges in neural networks learning multiple tasks in sequence.
method Linear teacher-student model with latent factors, derived analytical expression.
result Two principles for optimal task order: least representative first and dissimilar adjacent tasks.
Theory of learning with weight-distribution constraints.
problem Understanding how structure influences function in neural networks.
method Statistical mechanical theory and optimal transport.
result Reduction in capacity due to constrained weight-distribution is related to Wasserstein distance.
Expanding neural networks improves their learning from noisy data.
problem Improving neural network performance in noisy conditions.
method Sparse expansion of neural network inputs, followed by pruning, enhances generalization.
result Sparse expansion of neural networks improves generalization performance, even after pruning.
We develop a statistical mechanical approach based on the replica method to study the design space of deep and wide neural networks constrained to meet a large number of training data. Specifically, we analyze the configuration space of the synaptic weights and neurons in the hidden layers in a simple feed-forward perc…
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.
Paper generalizes teacher-student model for realistic data.
problem Capturing learning curves for realistic datasets.
method Introduces a Gaussian covariate generalization of the teacher-student model.
result Generalized model captures learning curves for various realistic data sets.
Study shows how task similarity affects forgetting in teacher-student setup.
problem Catastrophic forgetting in continual learning.
method Extended teacher-student setup to multiple teachers, analyzing similarity between tasks.
result Task similarity, whether at readouts or features, influences forgetting and transfer.
Statistical physics explains deep learning's feature learning capacity.
problem Understanding neural networks' ability to learn complex features.
method Study of a multi-layer perceptron in the interpolation regime.
result Optimal learning requires specialization across layers and neurons.
Two-layer ReLU networks outperform kernel methods in teacher-student settings.
problem Understanding the excess risk of two-layer ReLU neural networks in teacher-student models.
method Investigated a two-phase training process for a student network, comparing it to kernel methods.
result The student network reaches near-global optimality and outperforms kernel methods in minimax optimal rate.
Study analyzes catastrophic forgetting in continual learning using teacher-student networks.
problem Catastrophic forgetting in continuously learning systems.
method Teacher-student learning framework, similarity of input distributions and target functions.
result Network can avoid catastrophic forgetting with small input distribution similarity and large target function similarity.
A new training method improves MLIPs for faster, lighter simulations.
problem High computational and memory costs of complex MLIPs for large-scale MD simulations.
method Teacher-student training framework using latent atomic energy knowledge.
result Lightweight student MLIPs achieve faster MD speeds and comparable accuracy to teachers.
Paper analyzes how neural networks learn from a teacher in a specific setting.
problem Understanding how two-layer ReLU neural networks learn from a teacher in a regression model.
method Used gradient descent with specific regularization and over-parameterization, combined with measure representation and sparse estimation.
result Student network can identify teacher network parameters with high probability via gradient descent.
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…
Analyzes Hessian spectrum for neural networks near optimal learning.
problem Understanding learning dynamics near optimal points in neural networks.
method Characterizes Hessian eigenspectrum for teacher-student problems, using analytical and numerical methods.
result The rank of the Hessian matrix determines effective number of parameters for non-linear networks.
Stochastic Gradient Descent phases explained for deep networks.
problem Understanding the different regimes of SGD in deep learning.
method Teacher-student perceptron model, phase diagram analysis.
result SGD phases separated by batch size B∗, scaling with training set size P. 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.
Randomly sampled interpolators achieve zero generalization error with enough data.
problem Understanding the high generalization ability of machine learning models.
method Algebraic geometry tools to prove zero generalization error for random interpolators.
result Generalization error of randomly sampled interpolators becomes zero once the number of training samples exceeds a geometric threshold.
Deep neural networks outperform traditional methods in high-dimensional classification.
problem Understanding the empirical success of deep neural networks in high-dimensional classification.
method Proposed a teacher-student framework with Bayes classifier as ReLU neural networks, derived convergence rates for 0-1 and hinge losses.
result Sharp rate of convergence for classifiers trained using 0-1 or hinge loss, with Od(n−2/3) or Od(n−1) under separable data distribution. Study online learner attacks by manipulating labels, revealing critical thresholds.
problem Adversarial attacks on online learners, especially label manipulation.
method Control-theoretical perspective, theoretical analysis, empirical study.
result Discontinuous transition in learner's accuracy occurs at a critical threshold.
High-dimensional data in many machine learning applications leads to computational and analytical complexities. Feature selection provides an effective way for solving these problems by removing irrelevant and redundant features, thus reducing model complexity and improving accuracy and generalization capability of the…
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…
Deep convolutional neural networks have been widely used in numerous applications, but their demanding storage and computational resource requirements prevent their applications on mobile devices. Knowledge distillation aims to optimize a portable student network by taking the knowledge from a well-trained heavy teache…
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.
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.
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.
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…
Superpixel-mix enhances reliability in semantic segmentation.
problem Improving reliability in real-world semantic segmentation.
method Superpixel-mix, a new data augmentation method with teacher-student consistency training.
result Superpixel-mix achieves state-of-the-art results in semi-supervised semantic segmentation.
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 …
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.
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.
For real-world speech recognition applications, noise robustness is still a challenge. In this work, we adopt the teacher-student (T/S) learning technique using a parallel clean and noisy corpus for improving automatic speech recognition (ASR) performance under multimedia noise. On top of that, we apply a logits select…
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.
Vision algorithms capable of interpreting scenes from a real-time video stream are necessary for computer-assisted surgery systems to achieve context-aware behavior. In laparoscopic procedures one particular algorithm needed for such systems is the identification of surgical phases, for which the current state of the a…
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.
Superposition accelerates training to a universal power-law exponent.
problem Training dynamics in neural networks.
method Teacher-student framework and analytic theory.
result Superposition leads to a universal power-law exponent of ~1, independent of data and channel statistics.
Approach for biosensor condition detection using domain adaptation.
problem Limited clinical data for biosensor condition detection.
method Teacher-student adaptation of deep learning models.
result Significantly outperforms other methods on synthetic and real-world datasets.
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.
Linear models can grok without understanding, improving generalization.
problem Understanding the phenomenon of grokking in linear models.
method Analytical and numerical derivation of training and generalization dynamics in linear networks.
result Grokking can occur in linear networks without reaching understanding, and its timing depends on various parameters.