Unified formula for training dynamics of linear networks combining lazy and balanced regimes.
problem Training dynamics of linear networks in two distinct setups: lazy and balanced/active.
method Unified formula for the evolution of the learned matrix, combining lazy and balanced regimes.
result Unified formula allows for rapid convergence and low rank bias, proving a complete phase diagram.
Three training regimes found for scale-invariant neural networks on the sphere.
problem Training scale-invariant neural networks on the sphere with varying effective learning rate.
method Investigated three regimes of training: convergence, chaotic equilibrium, and divergence.
result Discovered three distinct training regimes with unique characteristics.
Study of two-layer ReLU neural network phase diagram at infinite-width limit.
problem Characterize the dynamical regimes of two-layer ReLU neural networks.
method Combining experimental and theoretical approaches, including phase diagram analogy.
result Identification of three regimes: linear, critical, and condensed.
Paper analyzes Gibbs and Langevin Monte Carlo for interpolation regime, showing generalization from low errors.
problem Analyzing Gibbs and Langevin Monte Carlo in overparameterized interpolation regime.
method Data-dependent bounds and stability under approximation with Langevin Monte Carlo.
result Generalization is signaled by small training errors in noisy regime, with bounds stable under approximation.
The paper identifies five extreme learning regimes for large linear autoencoders.
problem Understanding the learning dynamics of large weight-tied linear autoencoders.
method Formal loss-expansion hierarchy and analysis of gradient flow.
result Five extreme regimes associated with faces of a triangular prism.
We discuss the approximation of the value function for infinite-horizon discounted Markov Reward Processes (MRP) with nonlinear functions trained with the Temporal-Difference (TD) learning algorithm. We first consider this problem under a certain scaling of the approximating function, leading to a regime called lazy tr…
We study the supervised learning problem under either of the following two models: (1) Feature vectors xi are d-dimensional Gaussians and responses are yi=f∗(xi) for f∗ an unknown quadratic function; (2) Feature vectors xi are distributed as a mixture of two $…
Two distinct limits for deep learning have been derived as the network width h→∞, depending on how the weights of the last layer scale with h. In the Neural Tangent Kernel (NTK) limit, the dynamics becomes linear in the weights and is described by a frozen kernel Θ. By contrast, in the Mean-Field …
Two distinct phases of deep learning training improve model generalization.
problem Optimization and generalization in deep learning models.
method Isolating two phases of training: large-step and small-step, and tailoring training algorithms to each.
result Training algorithms optimized for each phase significantly simplify learning rate schedules.
Paper addresses uncertainty in model generalization under regime shifts.
problem Uncertainty in model generalization under regime changes.
method Proposes a framework to quantify and separate regime mismatch and sensitivity.
result Obtains exact decomposition and minimax lower bound for regime-aware models.
Study on how initialization scale affects neural network training regimes.
problem Understanding the transition between kernel and rich regimes in overparametrized models.
method Analysis of simple depth-D models and empirical testing on complex models.
result Scale of initialization controls transition between kernel and rich regimes.
Deep networks become equivalent to linear models in large data regimes.
problem Understanding the behavior of deep neural networks in large data regimes.
method Information-theoretic analysis of fully-trained neural networks in proportional scaling regime.
result Proves deep Gaussian equivalence principle, showing deep networks can be simplified to linear models.
Study on rich regime training in deep learning, finding active parameters in bottom layers.
problem Understanding the practical success of deep learning models.
method Empirical study on rich regime training with benchmark datasets, re-initialization analysis, and probabilistic Layer-Wise Sparse SGD.
result Probabilistic Layer-Wise Sparse SGD matches vanilla SGD's generalization performance with improved efficiency.
Study examines how training regime affects neural networks' forgetting.
problem Catastrophic forgetting in neural networks when learning multiple tasks sequentially.
method Analyzes the impact of different training regimes (learning rate, batch size, regularization) on forgetting.
result Training regimes that widen tasks' local minima help prevent catastrophic forgetting.
Elman-type RNNs converge to globally optimal solutions in the mean-field regime.
problem Optimizing feature learning in wide RNNs.
method Analysis of gradient descent dynamics and mean-field limits.
result Fixed points of infinite-width dynamics are globally optimal.
This work shows linear convergence for two-layer neural networks in mean-field regime.
problem Optimizing two-layer neural networks in the mean-field regime.
method Mean-field analysis and continuous-time noisy gradient descent.
result Establishes linear convergence rate for two-layer neural networks.
New insights into how neural networks learn features, especially when they are very wide.
problem Understanding how gradient flow in wide neural networks selects solutions, especially in the feature-learning regime.
method Axiomatizing the canonical regularizer as a function-space energy and lift, and deriving geodesic ridge for the feature-learning regime.
result Gradient flow in feature-learning networks biases towards ridge regularization, distorting the inductive bias and damaging pretrained networks.
It has been observed \citep{zhang2016understanding} that deep neural networks can memorize: they achieve 100\% accuracy on training data. Recent theoretical results explained such behavior in highly overparametrized regimes, where the number of neurons in each layer is larger than the number of training samples. In thi…
Study proposes adaptive RL for dynamic portfolio optimization.
problem Traditional portfolio optimization models fail to adapt to regime shifts.
method Regime-aware reinforcement learning framework with hybrid observations and constrained reward functions.
result Transformer PPO achieves highest risk-adjusted returns, while LSTM variants offer a good balance.
Gradient descent can find better tensor decompositions than lazy training in over-parameterized settings.
problem Finding better tensor decompositions in over-parameterized settings.
method Gradient descent on over-parameterized tensor decomposition problems.
result Gradient descent can find an approximate tensor decomposition with rank m=O∗(r2.5llogd), while lazy training requires m=Ω(dl−1). Gradient descent converges to minimum Bayes risk for two-layer ReLU networks in mean field regime.
problem Training two-layer ReLU networks using gradient descent in the mean field regime.
method Describes a condition for convergence to minimum Bayes risk, extending previous results to ReLU-activated networks.
result The condition for convergence does not depend on initialization and concerns weak convergence of network realization.
A remarkable recent discovery in machine learning has been that deep neural networks can achieve impressive performance (in terms of both lower training error and higher generalization capacity) in the regime where they are massively over-parameterized. Consequently, over the past year, the community has devoted growin…
We train a network to generate mappings between training sets and classification policies (a 'classifier generator') by conditioning on the entire training set via an attentional mechanism. The network is directly optimized for test set performance on an training set of related tasks, which is then transferred to unsee…
Transfer learning improves image classifier performance in data-starved regimes.
problem Deploying image classifiers in domains with limited labeled data.
method Transfer learning with deep neural networks, focusing on feature reuse and overparameterization.
result Transfer learning enhances CNN performance in data-starved regimes.
More training data can hurt the generalization of adversarially robust models.
problem The challenge of balancing adversarial robustness and generalization in machine learning models.
method Investigation of three regimes based on adversary strength and empirical studies on various models.
result More training data can hurt the generalization of adversarially robust models in different regimes.
Proves convergence of neural networks in a two-timescale regime.
problem Training dynamics of shallow neural networks.
method Two-timescale regime analysis of gradient flow.
result Gradient flow converges to global optimum in non-convex optimization.
This paper improves adversarial robustness of deep learning models.
problem Vulnerability of machine learning models to adversarial perturbations.
method Analyzes adversarial training for linear regression and neural networks, incorporating L1 penalty.
result Incorporating L1 penalty leads to consistent adversarially robust estimation in high-dimensional settings.
Study on adversarial robustness in neural networks across initialization and training phases.
problem Understanding adversarial robustness in neural networks during different learning stages.
method Analyzes adversarial robustness in various scenarios of over-parameterized networks with quadratic targets and infinite samples.
result Robustness can worsen when test error improves, and vice versa, revealing new tradeoffs.
The paper identifies conditions for trend reversal in classification tasks.
problem Trend reversal in classification scores and dataset values.
method Algebraic conditions and numerical results for ridge regression.
result Existence of pathological regularization regimes for certain dataset conditions.
A recent line of work studies overparametrized neural networks in the "kernel regime," i.e. when the network behaves during training as a kernelized linear predictor, and thus training with gradient descent has the effect of finding the minimum RKHS norm solution. This stands in contrast to other studies which demonstr…
Training neural networks on image datasets generally require extensive experimentation to find the optimal learning rate regime. Especially, for the cases of adversarial training or for training a newly synthesized model, one would not know the best learning rate regime beforehand. We propose an automated algorithm for…
Enhances portfolio construction with tailored regime forecasts for individual assets.
problem Traditional portfolio construction methods fail to account for asset-specific market conditions.
method Hybrid framework combining unsupervised and supervised learning for regime identification and forecasting.
result Outperforms traditional portfolio models across various asset classes.
Paper optimizes change-point detection using learned distributions from training sequences.
problem Optimal change-point detection with unknown pre- and post-change distributions.
method Designs a change-point estimator using training sequences and test sequences.
result Optimal confidence width characterized as a function of undetected error.
We analyze architectural features of Deep Neural Networks (DNNs) using the so-called Neural Tangent Kernel (NTK), which describes the training and generalization of DNNs in the infinite-width setting. In this setting, we show that for fully-connected DNNs, as the depth grows, two regimes appear: "order", where the (sca…
A new method for pricing European options in changing market conditions.
problem Lack of closed-form solutions for pricing European options in regime-switching models.
method Physics-informed residual learning (PIRL) for efficient option pricing.
result PIRL eliminates the need for retraining and offers near-instantaneous pricing.
Deep learning models generalize by extending decision boundaries outside the convex hull of training data.
problem Understanding how deep learning models generalize beyond their training data.
method Investigation of decision boundaries inside and outside the convex hull of training sets, using various neural network architectures and training regimes.
result Over-parameterization is necessary for deep learning models to extend decision boundaries outside the convex hull of their training data.
3D convolutional neural networks are difficult to train because they are parameter-expensive and data-hungry. To solve these problems we propose a simple technique for learning 3D convolutional kernels efficiently requiring less training data. We achieve this by factorizing the 3D kernel along the temporal dimension, r…
New findings on kernel regression in the quadratic regime, improving understanding of machine learning models.
problem Understanding kernel ridge regression in the quadratic asymptotic regime.
method Extended study of kernel regression to the quadratic regime, establishing approximation bounds and spectral distributions.
result Broad class of inner-product kernels exhibit behavior similar to a quadratic kernel, with precise asymptotic training and test errors characterized.
Orthogonal initialization does not speed up training in ultra-wide neural networks.
problem Exploring the effect of orthogonal initialization on training speed in deep neural networks.
method Study of neural tangent kernel dynamics in FCNs and CNNs with orthogonal initialization.
result The NTK of orthogonally-initialized networks remains constant during training, suggesting no speedup in the NTK regime.
The paper proposes a machine learning framework for portfolio optimization with limited data.
problem Low data environments and regime uncertainty in portfolio optimization.
method A teacher-student learning pipeline with CVaR optimizer generating supervisory labels and neural models trained on real and synthetic data.
result Student models can match or outperform the CVaR teacher and achieve improved robustness under regime shifts.
A fairly comprehensive analysis is presented for the gradient descent dynamics for training two-layer neural network models in the situation when the parameters in both layers are updated. General initialization schemes as well as general regimes for the network width and training data size are considered. In the over-…
Recent work by Jacot et al. (2018) has shown that training a neural network using gradient descent in parameter space is related to kernel gradient descent in function space with respect to the Neural Tangent Kernel (NTK). Lee et al. (2019) built on this result by establishing that the output of a neural network traine…
Deep learning solves wave-based inverse problems, including super-resolution imaging.
problem Solving inverse wave scattering problems across all length scales.
method Wide-band butterfly network coupled with dynamic noise injection.
result Framework successfully solves super-resolution imaging problems.
This paper studies nonlinear representation learning dynamics beyond the NTK regime.
problem Efficient reasoning and inference in raw sensory data representations.
method Identifies common model structure assumption and data-architecture alignment condition for global convergence and optimality.
result Theoretical framework explains network size effects and provides practical model structure guidelines.
Theoretical analysis explains why models generalize after overfitting in modular addition.
problem Understanding why models generalize after overfitting in modular addition.
method Theoretical analysis and gradient descent behavior of two-layer quadratic networks and Transformers.
result Two-layer quadratic networks and simple Transformers generalize well after initially overfitting, indicating grokking.
We study the limits and methods of training two-layer autoencoders.
problem Understanding the limits and methods of training two-layer autoencoders.
method Focus on non-linear two-layer autoencoders trained in the proportional regime, using gradient methods.
result Gradient methods achieve the minimizers of the population risk and reveal the structure of the features.
Gradient descent learns useful features even in the NTK regime.
problem The ability of neural networks to learn useful features.
method Local convergence analysis of gradient descent with regularization.
result Gradient descent can capture ground-truth directions for feature learning even after the loss threshold is reached.
Neural networks encode inputs deterministically and categorically, behaving like hash encoders.
problem Understanding the encoding properties of neural networks.
method Analyzed the input space partitioned by ReLU-like activations in neural networks.
result Neural networks can be represented by unique activation patterns, similar to hash encoders.