Lazy training and mean field regimes studied for TD learning with nonlinear function approximation.
problem Approximating value function for MRP with TD learning and nonlinear functions.
method Lazy training and mean field scaling of parameters analyzed for convergence.
result Lazy training leads to exponential convergence to local/global minimizers, while mean field scaling results in all fixed points being minimizers.
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.
New private algorithms for online learning improve regret in high privacy regimes.
problem Private online learning from experts and convex optimization.
method Transformed lazy algorithms for differential privacy.
result Improved regret bounds for DP-OPE and DP-OCO.
Lazy neural networks are vulnerable to adversarial attacks.
problem Adversarial robustness issues in lazy training models.
method Extending recent work on adversarial examples to lazy training models.
result Over-parametrized neural networks that generalize well remain vulnerable to single-step gradient ascent attacks.
Deep networks prioritize easier examples over harder ones, leading to faster training.
problem Understanding how deep networks prioritize examples of varying difficulty.
method Investigated the effect of linear vs non-linear learning modes on example difficulty.
result Non-linear dynamics tend to sequentialize the learning of examples of increasing difficulty.
Lazy-CFR improves CFR's efficiency and performance in imperfect information games.
problem Efficiency and performance in imperfect information games with imperfect information.
method Lazy update technique to avoid full traversal of game tree, resulting in a more efficient CFR variant.
result Lazy-CFR achieves better convergence and significantly outperforms vanilla CFR in experiments.
Study shows optimal model performance at critical level of feature learning.
problem Catastrophic forgetting in neural networks, especially in non-stationary environments.
method Systematic study on model scale and feature learning, using dynamical mean field theory.
result Optimal performance achieved at a critical level of feature learning, dependent on task non-stationarity and model scale.
Quantum machine learning faces 'laziness' and 'barren plateaus', but noise can mitigate the latter.
problem Quantum machine learning's loss function landscape issues.
method Theoretical analysis of quantum variational circuits, neural tangent kernels, and noise effects.
result Noise can mitigate barren plateaus in quantum machine learning.
Lazy labels enable deep learning for microscopy segmentation without full annotation.
problem Lack of pixel-wise annotations limits fully supervised learning for bioimage segmentation.
method Lazy labels combined with coarse labels for training a deep neural network.
result Model achieves accurate segmentation with minimal pixel-wise annotations.
Grokking occurs when neural networks transition from lazy to rich training dynamics, fitting initial features before generalizing.
problem Understanding why neural networks exhibit early train loss decrease without corresponding test loss improvement.
method Analyzing vanilla gradient descent on polynomial regression with a two-layer neural network, identifying sufficient statistics for test loss.
result Grokking arises when a network first attempts to fit a kernel regression solution with initial features, followed by late-time feature learning.
Clapping reduces memory usage in distributed optimization by reusing data samples.
problem Significant communication overhead and impractical memory overhead in pipeline-parallel distributed optimization.
method Lazy sampling strategy to reuse data samples across steps, supporting convergence without unbiased gradient assumptions.
result Clapping achieves convergence in few-epoch or online training regimes without sample-size memory overhead.
The study distinguishes between lazy and feature training limits in deep neural networks.
problem Understanding the dynamics of deep neural networks as they grow in width.
method Varying the scaling of weights in the last layer and observing the crossover between two limits.
result Two distinct limits (NTK and Mean-Field) are identified, each with its own dynamics and kernel evolution.
Stochastic principal component analysis (SPCA) has become a popular dimensionality reduction strategy for large, high-dimensional datasets. We derive a simplified algorithm, called Lazy SPCA, which has reduced computational complexity and is better suited for large-scale distributed computation. We prove that SPCA and …
A method learns common bias for multiple low-variance tasks without hyper-parameter tuning.
problem Learning common bias for multiple low-variance tasks without manual tuning.
method Two variants of online learning methods (aggressive and lazy) that update bias after each datapoint or at the end of each task.
result Across-tasks regret bound derived for the method, showing faster rates for aggressive variant and standard rates for lazy variant.
LazyBum uses lazy propositionalization to learn from relational data.
problem Applying propositional learners to relational data.
method Interleaves decision tree learning with lazy propositionalization.
result Achieves comparable accuracy to other methods with lower execution time.
Framework uses low-dimensional maps to solve high-dimensional Bayesian inference problems.
problem High-dimensional Bayesian inference problems.
method Structure-exploiting lazy maps and flows, focusing on low-dimensional subspace.
result Weak convergence of generated distributions to the posterior.
A new method simulates a lazy version of a Markov chain for empirical inference.
problem Estimating and testing unknown Markov chains with limited data.
method Simulates an α-lazy version of an unknown Markov chain, making it ergodic.
result The pseudo spectral gap can be applied to non-ergodic Markov chains.
Study introduces a new investment strategy model using lazy factor and probability weights.
problem Optimizing investment strategies in volatile markets with transaction costs.
method Combines Price Portfolio Forecasting and Mean-Variance Models with Transaction Costs, using probability weights as laziness factor coefficients.
result Model demonstrates adaptability and generalizability in transforming investment strategies.
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 ∗ ( r 2.5 l log d ) m = O^*(r^{2.5l}\log d) m = O ∗ ( r 2.5 l log d ) , while lazy training requires m = Ω ( d l − 1 ) m = Ω(d^{l-1}) m = Ω ( d l − 1 ) . Lazy, perfectly informed investors trade infrequently due to costs.
problem The paradox of an omniscient yet lazy investor trading infrequently.
method Formalized the paradox using geometric and fractional Brownian motion models, derived closed-form profit functions, and proved existence and uniqueness of the optimal trading frequency.
result The optimal trading frequency can be interpreted through the fractal dimension of the price path.
Transformers learn rich in-context dependencies efficiently.
problem Understanding how transformers learn long-range dependencies efficiently.
method Approximation and dynamics analysis of induction head mechanisms.
result Abrupt transition from lazy to rich mechanisms during training.
Proposes an efficient algorithm for identifying important features in binary classification.
problem Understanding explainability of deep neural networks in binary classification.
method Variable-importance framework combined with lazy training.
result Achieves well-controlled error rates with minimal assumptions.
Deep learning and lazy learner improve early sepsis detection.
problem Detecting sepsis early in high-resolution ICU records.
method Deep learning model with temporal convolutional network and Gaussian Process Adapter; lazy learner with dynamic time warping.
result Improves sepsis detection from 0.25 to 0.40 AUPRC 7 hours before onset.
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.
Deep and wide ReLU networks learn data-dependent features even in the lazy training regime.
problem Understanding the behavior of neural networks with finite depth and width.
method Analyzing the mean and variance of the neural tangent kernel (NTK) in a randomly initialized ReLU network.
result The NTK has a non-trivial evolution during training, with the mean of its first SGD update being exponential in the ratio of depth to width.
Lazy Gradient Descent outperforms existing polytope algorithms in pseudo-regret.
problem Achieving optimal regret bounds on polytopes efficiently.
method Lazy Online Gradient Descent on polytopes.
result Proves O ( 1 ) O(1) O ( 1 ) pseudo-regret against i.i.d opponents. In this work we introduce a conditional accelerated lazy stochastic gradient descent algorithm with optimal number of calls to a stochastic first-order oracle and convergence rate O ( 1 ε 2 ) O\left(\frac{1}{\varepsilon^2}\right) O ( ε 2 1 ) improving over the projection-free, Online Frank-Wolfe based stochastic gradient descent of Hazan an…
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.
We explore how neural networks train to zero loss, focusing on initial scale.
problem Understanding neural network training dynamics and zero loss.
method Macroscopic limits analysis of gradient descent dynamics.
result Gradient descent can drive deep neural networks to zero loss regardless of initialization.
Exact solutions reveal how unbalanced initializations promote rapid feature learning in neural networks.
problem Understanding how neural networks efficiently extract features from data.
method Deriving exact solutions to a minimal model of neural networks transitioning between lazy and rich learning regimes.
result Unbalanced layer-specific initialization variances and learning rates determine the degree of feature learning.
Study on network-valued processes with asynchronous updates, proving consistency in community and changepoint estimation.
problem Understanding the behavior of network-valued stochastic processes with asynchronous updates.
method Analysis of concentration properties of aggregated adjacency and Laplacian matrices for lazy network-valued stochastic processes.
result Demonstrates consistency of estimators in community and changepoint estimation problems.
Use simplified layerwise linear models to understand neural dynamics.
problem Complex neural network dynamics are hard to grasp.
method Apply simplified layerwise linear models to explain neural phenomena.
result Simplified models explain neural collapse, emergence, etc.
New method converts and optimizes sampling schedules for generative models.
problem Optimizing sampling schedules for generative models like flows and diffusions.
method Unified framework for stochastic interpolants, including point mass schedules.
result Demonstrated efficient generation of images with fewer steps.
The paper tackles efficient online learning by achieving minimal regret with respect to the best expert.
problem Achieving minimal regret in online learning problems where the goal is to match the lowest regret of K experts.
method A lazy form of the online subgradient algorithm is used to achieve minimal regret in 'easy' regimes.
result Minimal regret strategies exist for some 'hard' regimes, and the algorithm retains an O ( n ) O(\sqrt{n}) O ( n ) worst-case regret guarantee. ABC algorithms involve a large number of simulations from the model of interest, which can be very computationally costly. This paper summarises the lazy ABC algorithm of Prangle (2015), which reduces the computational demand by abandoning many unpromising simulations before completion. By using a random stopping decis…
New algorithm for active exploration in bandit problems.
problem Active exploration in bandit problems.
method Gradient ascent with online lazy mirror ascent sampling rule.
result Asymptotically optimal and computationally efficient.
Deep networks generalize well even when they fit training data perfectly, thanks to overparametrization.
problem Understanding generalization in overparametrized deep networks.
method Random features regression, asymptotic analysis, ensemble averaging.
result Bias remains constant beyond the interpolation threshold, while variance components decay with overparametrization.
Study on how adversarial training affects neural network kernels and robustness.
problem Understanding and improving adversarial robustness in neural networks.
method Empirical study of the evolution of the empirical Neural Tangent Kernel (NTK) under standard and adversarial training.
result Adversarial training leads to a new kernel that provides robustness, even when non-robust training is performed on top of it.
Auto-CEI improves LLM reasoning by balancing assertiveness and conservativeness.
problem Hallucinations and laziness in LLM reasoning tasks.
method Expert Iteration explores reasoning trajectories, guiding incorrect paths back on track and promoting appropriate 'I don't know' responses.
result Auto-CEI achieves superior alignment in logical reasoning, mathematics, and planning tasks.
Analysis of deep neural networks under various learning rules reveals dynamics of feature and prediction learning.
problem Understanding how different learning rules affect feature and prediction dynamics in deep neural networks.
method Analysis of infinite-width deep networks trained with gradient descent and various learning rules.
result The evolution of the output function is governed by an effective neural tangent kernel (eNTK), which varies depending on the learning rule and training regime.
Mirror flow in shallow neural networks shows similar implicit bias to gradient flow, with key differences in curvature penalties.
problem Analyzing implicit bias in shallow neural networks with mirror flow.
method Characterization through variational problems and scaled potentials.
result Mirror flow with scaled potentials induces a rich class of biases not captured by RKHS norms.
Theory captures feature learning effects in finite CNNs.
problem Feature learning in finite deep neural networks.
method Derive a self-consistent Gaussian Process theory.
result Good agreement with experiments and sharp transition between regimes.
We study Bayesian optimal control of a general class of smoothly parameterized Markov decision problems. Since computing the optimal control is computationally expensive, we design an algorithm that trades off performance for computational efficiency. The algorithm is a lazy posterior sampling method that maintains a d…
Neural networks can learn kernel machines with a data-dependent kernel.
problem Can neural networks in the rich feature learning regime learn a kernel machine?
method Demonstrated silent alignment effect in neural networks, showing they can learn a kernel machine with a data-dependent kernel.
result Neural networks in the rich feature learning regime can learn a kernel machine with a data-dependent kernel due to silent alignment.
Neural networks learn task-specific features, influenced by nonlinearity.
problem Understanding the nature of task-dependent feature learning in neural networks.
method Investigation of fully-connected, wide neural networks using Bayesian framework.
result The nature of internal representations depends on neuronal nonlinearity, leading to analog, redundant, or sparse coding schemes.
Analyzes neural networks using linear models to understand their behavior.
problem Understanding multi-layer neural networks through linear models.
method Recalls and reviews four models: linear regression with concentrated features, kernel ridge regression, random feature model, and neural tangent model.
result Highlights limitations of linear theory and discusses approaches to overcome them.
LAZO reduces query complexity and variance in ZO methods.
problem High query complexity and variance in zeroth-order optimization.
method LAZO uses adaptive lazy queries to reduce variance and save queries.
result LAZO achieves lower regret and query complexity compared to existing methods.
Neural networks compress uninformative input directions, improving test error.
problem Data lie in a high-dimensional space but labels vary along a lower-dimensional manifold.
method One-hidden layer network trained with gradient descent, analyzing weight evolution and compression.
result Compression factor λ ∼ √p improves test error, with β Feature > β Lazy.