Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

94188281375 · Jun 202019922001200920172026
48 results for Inverse depth scaling

We prove a scaling limit theorem for the super-replication cost of options in a Cox--Ross--Rubinstein binomial model with transient price impact. The correct scaling turns out to keep the market depth parameter constant while resilience over fixed periods of time grows in inverse proportion with the duration between tr…

2018-10-17abs ↗pdf ↗

Training very deep networks is an important open problem in machine learning. One of many difficulties is that the norm of the back-propagated error gradient can grow or decay exponentially. Here we show that training very deep feed-forward networks (FFNs) is not as difficult as previously thought. Unlike when back-pro…

2014-12-19abs ↗pdf ↗

Unified spectral framework for μP under joint width-depth scaling.

problem Challenges in stable feature learning and HP transfer for width-depth scaled models.
method Developed a simple and unified spectral framework for μP under joint width-depth scaling.
result Unified and generalized μP formulation for practical architectures with multi-transformation branches.

Statistical analysis of algorithm unrolling for inverse problems.

problem Designing deep neural networks to solve inverse problems efficiently.
method Analysis of gradient descent network (GDN) unrolling depth and statistical performance.
result The optimal statistical performance of GDNs requires unrolling depth of order log(n)/log(ρ_n^-1), where ρ_n is the convergence rate.

This paper explores how neural network width and depth behave as they approach infinity.

problem Understanding the behavior of neural functions as width and depth go to infinity.
method Formal definition of commutativity framework, study of neural covariance kernel, novel proof techniques.
result Taking width and depth to infinity in a deep neural network with skip connections results in the same covariance structure, regardless of the order of taking limits.

Study how depth affects inference in deep Bayesian neural networks.

problem Understanding how depth impacts inference in overparameterized linear Bayesian neural networks.
method Interpreting finite deep linear Bayesian neural networks as scale mixtures of Gaussian process predictors.
result Advances analytical understanding of how depth affects inference in a simple class of Bayesian neural networks.

Unified learning-rate scale for CNNs and ResNets, avoiding depth imbalance.

problem Challenges in choosing an appropriate learning rate for deep networks, especially as depth increases.
method Introduces Arithmetic-Mean μμP (AM-μμP), constraining network-wide average pre-activation second moment to a constant scale, combined with residual-aware He fan-in initialization.
result Demonstrates a 3/2-3/2 scaling law for learning rates across depths, enabling zero-shot learning-rate transfer.

Theoretical limits of deep residual networks show consistent covariance structures.

problem Understanding the limits of deep residual networks.
method Analyzing the behavior of deep residual networks with skip connections as width and depth approach infinity.
result Theoretical analysis confirms that the covariance structure remains consistent regardless of the order of width and depth.

Deep networks with orthogonal weights show stable fluctuations, improving generalization and training speed.

problem Fluctuations in deep networks with Gaussian weights can impair training, especially in networks with depth comparable to width.
method Analytical and numerical studies of fully-connected networks with orthogonal weight initialization and tanh activations.
result Rectangular networks with orthogonal weights have stable fluctuations independent of network depth, leading to better generalization and training speed.

New insights into how depth and width affect in-context learning in deep models.

problem Understanding how various resources impact in-context learning in deep models.
method Analyzed linear regression in a deep linear self-attention model, varying resources like depth, width, context length, and training steps.
result Increasing depth improves in-context learning even at infinite context length, contrary to previous findings.

We study the behavior of untrained neural networks whose weights and biases are randomly distributed using mean field theory. We show the existence of depth scales that naturally limit the maximum depth of signal propagation through these random networks. Our main practical result is to show that random networks may be…

2016-11-04abs ↗pdf ↗

We study the price impact of order book events - limit orders, market orders and cancelations - using the NYSE TAQ data for 50 U.S. stocks. We show that, over short time intervals, price changes are mainly driven by the order flow imbalance, defined as the imbalance between supply and demand at the best bid and ask pri…

2010-11-29abs ↗pdf ↗

Existing depth separation results for constant-depth networks essentially show that certain radial functions in Rd\mathbb{R}^d, which can be easily approximated with depth 33 networks, cannot be approximated by depth 22 networks, even up to constant accuracy, unless their size is exponential in dd. However, the func…

2019-04-15abs ↗pdf ↗

Residual networks with depthwise hyperparameter scaling transfer optimal hyperparameters across width and depth.

problem The challenge of hyperparameter tuning in deep learning, especially for large models.
method Combining μμP parameterization with residual networks having a residual branch scale of 1/extdepth1/\sqrt{ ext{depth}}.
result Optimal hyperparameters transfer across width and depth in residual networks trained with this parameterization.

Study on feature learning dynamics in infinite-depth neural networks, focusing on ResNets.

problem Understanding how features evolve during training in deep neural networks, especially in the large-depth limit.
method Conditional Gaussian representations and SDE system with decoupled backward weights.
result Depth-induced suppression of forward-backward coupling in infinite-depth networks, leading to a decoupled forward-backward SDE system.

We study inverse problems consisting on determining medium properties using the responses to probing waves from the machine learning point of view. Based on the understanding of propagation of waves and their nonlinear interactions, we construct a deep convolutional neural network in which the parameters are used to cl…

2018-11-09abs ↗pdf ↗

Self-attention models benefit equally from width and depth, but beyond a certain point, depth becomes less efficient.

problem Understanding the optimal balance between depth and width in self-attention models.
method Theoretical predictions and empirical ablations on networks of varying depths and widths.
result An optimal width of 30K is recommended for a 1-Trillion parameter network, marking a significant width for self-attention models.

SHINE uses forward pass quasi-Newton matrices to approximate Jacobian inverses for faster bi-level optimization.

problem Efficiently solving bi-level optimization problems with large Jacobian matrices.
method Proposes using quasi-Newton matrices from the forward pass to approximate the inverse Jacobian matrix.
result Empirically shows SHINE reduces computational cost of the backward pass for various problems.

Proposes an online method for high-dimensional streaming data.

problem Increasing variable dimensions with sample size in online kernel sliced inverse regression.
method Introduces approximate linear dependence condition and dictionary variable sets to address the problem. Transforms into online generalized eigen-decomposition problem and uses stochastic optimization for updates.
result Achieves close performance to batch processing kernel sliced inverse regression.

Study infinite-depth limits of neural networks with fixed width.

problem Understanding the behavior of neural networks as depth increases with fixed width.
method Analyzing finite-width residual networks with random Gaussian weights, focusing on the infinite-depth limit.
result The pre-activations converge to a zero-drift diffusion process, differing from the infinite-width limit.

Iterative learning to infer approaches have become popular solvers for inverse problems. However, their memory requirements during training grow linearly with model depth, limiting in practice model expressiveness. In this work, we propose an iterative inverse model with constant memory that relies on invertible networ…

2019-11-25abs ↗pdf ↗

Residual networks' depth is mathematically equivalent to expanding an implicit ensemble size.

problem Understanding why deep residual networks are effective.
method Formal analysis of residual networks as ensembles of shallow models.
result Increasing network depth is equivalent to expanding the size of an implicit ensemble, revealing a hierarchical structure.

Scaling ResNets requires careful consideration of the layer depth and output scaling factors.

problem Avoiding vanishing or exploding gradients in deep ResNets as depth increases.
method Probabilistic analysis and continuous-time limit interpretation of ResNets.
result The optimal scaling factor is αL=1Lα_L = \frac{1}{\sqrt{L}} for standard i.i.d. initializations.

New scaling framework for MoE architectures ensures stability and optimal performance at scale.

problem Lack of principled understanding of how hyperparameters should scale in MoE architectures.
method Developed a novel Dynamical Mean Field Theory (DMFT) for three scaling regimes of MoE architectures.
result Derived Maximally Scale-Stable Parameterization (MSSP) for SGD and Adam, providing robust learning rate transfer and monotonic improvement with scale.

Study reveals how Fisher information changes with network depth, finding it grows linearly.

problem Understanding the trainability of deep neural networks (DNNs).
method Investigates the spectral distribution of the conditional Fisher information matrix (FIM) for fully-connected networks achieving dynamical isometry.
result The conditional FIM's spectrum concentrates around the maximum and grows linearly with depth.

New method improves reliability of depth estimation models.

problem Uncertainty quantification in large-scale vision models.
method Parameter-efficient Bayesian neural networks with PEFT methods.
result Combining PEFT methods with Bayesian inference enhances predictive performance.

Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this limitation, self-supervised learning has emerged as a promising alternative for training models to perform monocular depth estimation. In this paper, we propose a set of improvements, which together result in both quantitatively and …

2018-06-04abs ↗pdf ↗

Pruned neural networks' error scales predictably with architecture and task.

problem Understanding the predictability of pruning across different scales and architectures.
method Functionally approximated the error of pruned networks, showing it is predictable in terms of invariant tying width, depth, and pruning level.
result The error of pruned networks follows a scaling law with interpretable coefficients that depend on architecture and task.

Proves depth 2 neural networks can't approximate certain functions as well as depth 3 networks.

problem Approximating functions with depth 2 networks in high dimensions.
method Lower bound proof using worst-to-average-case random self-reducibility.
result Proves depth 2 networks can't approximate certain functions as well as depth 3 networks, resolving an open problem.

Deep networks improve by progressively refining approximations at each layer.

problem Standard approximation theory doesn't explain the role of intermediate layers in deep neural networks.
method Developed a mixed-activation architecture with a geometric scale interpretation of depth.
result Each intermediate layer approximates the target function with a geometric rate.

We prove the precise scaling, at finite depth and width, for the mean and variance of the neural tangent kernel (NTK) in a randomly initialized ReLU network. The standard deviation is exponential in the ratio of network depth to width. Thus, even in the limit of infinite overparameterization, the NTK is not determinist…

2019-09-13abs ↗pdf ↗

The paper analyzes Tikhonov regularization in Hilbert scales for statistical inverse problems.

problem Statistical inverse problems in Hilbert scales with general noise.
method Tikhonov regularization scheme with conditional stability estimates and high probability error bounds.
result Explicit rates of convergence for oversmoothing and regular cases over defined regularity classes.

Study reveals how depth of reasoning affects generalization in models.

problem Understanding scaling behavior of generalization with CoT depth.
method Theoretical model of CoT in linear regression using random matrix theory.
result Sharp phase transition between exponential and polynomial improvement, saturation, and overthinking.

Proves rigidity of circle packings in the plane, generalizing previous work.

problem Rigidity of infinite inversive distance circle packings in the plane.
method Maximal principle for generic weighted Delaunay inversive distance circle packings and ring lemma for inversive distance circle packings in hexagonal triangulated plane.
result Proves Bowers-Stephenson's conjecture for inversive distance circle packings.

Deep learning model improves seismic rock property estimation.

problem Estimating reservoir rock properties from seismic reflection data.
method Proposes a deep learning-based seismic inversion workflow that models seismic traces spatiotemporally.
result Achieves best performance on SEAM dataset with r2r^{2} coefficient of 79.77\%

Neural operators improve solving Helmholtz equation for various wave speeds.

problem Neural operators struggle with out-of-distribution scenarios for high-frequency waves.
method Proposed a subfamily of neural operators with stochastic depth for enhanced approximation of the Helmholtz equation.
result Neural operators with stochastic depth outperform standard models in out-of-distribution scenarios.

CNN improves neutrino event reconstruction in IceCube DeepCore.

problem Difficulties in distinguishing muon neutrinos and reconstructing inelasticity at GeV scale energies.
method 2D Convolutional Neural Network exploiting time and depth translational symmetry.
result CNN model outperforms conventional methods for flavor identification and inelasticity reconstruction.

Uniform scaling limits in AdamW-trained transformers converge to ODEs.

problem Understanding the dynamics of large-depth transformers trained with AdamW.
method Modeling transformer dynamics as an interacting particle system coupled through attention, proving convergence to ODEs.
result The joint dynamics of hidden states and backpropagated variables converge uniformly to an ODE system.