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

4692138184 · Jun 202019922001200920172026
48 results for width maximization

The paper proves the existence of boundary minimal hypersurfaces in compact manifolds with boundary.

problem Existence of boundary minimal hypersurfaces in compact manifolds with boundary.
method Min-max theory applied to local maximizers of width in conformal classes.
result Existence of a sequence of properly embedded equidistributed boundary minimal hypersurfaces.

Maximal initial learning rate for deep ReLU networks identified.

problem Finding the optimal initial learning rate for deep neural networks.
method Simple approach to estimate maximal initial learning rate ηη^{\ast}, analyzing its behavior in constant-width fully-connected ReLU networks.
result Maximal initial learning rate ηη^{\ast} is well predicted as a power of depth × width, with specific conditions for network width and input layer training.

Polynomial neural networks explore thresholds for maximum expressiveness.

problem Understanding the limits of polynomial neural networks' expressiveness.
method Introducing activation degree threshold to measure network expressiveness and proving its existence and upper bounds.
result Polynomial neural networks with equi-width architectures achieve the maximum expressiveness.

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.

Proof of learning rate transfer in MLPs with μμP parameterization.

problem Understanding and optimizing learning rates in neural networks with different parameterizations.
method Theoretical analysis and empirical validation of learning rate transfer in MLPs with μμP, SP, and NTP parameterizations.
result The optimal learning rate converges to a non-zero constant as width goes to infinity under μμP, explaining learning rate transfer.

Bayesian linear networks reveal optimal depth and width trade-offs.

problem Understanding how depth, width, and dataset size affect model quality in linear networks.
method Zero noise Bayesian inference with Gaussian weight priors and mean squared error.
result Optimal predictions at infinite depth and maximized Bayesian model evidence at infinite depth.

Wide neural networks can degrade performance, contrary to conventional wisdom.

problem Understanding the limitations of increasing network width in neural networks.
method Using Deep Gaussian Processes to decouple capacity and width, analyzing their effects on representational power and non-Gaussianity.
result Wide neural networks can become less adaptable and more Gaussian, leading to performance degradation.

New analysis shows optimal embedding learning rate depends on vocabulary size, not just model width.

problem Optimal learning rate for language model embeddings is not well understood, especially with large vocabularies.
method Theoretical analysis of training dynamics, interpolation between μμP and LV regimes.
result Optimal embedding learning rate scales as Θ(width)Θ(\sqrt{width}) in the LV regime, not Θ(width)Θ(width) as μμP predicts.

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.

New framework explains fast transfer of hyperparameters across model scales.

problem Understanding and optimizing hyperparameters for large-scale models.
method Developed a conceptual framework for HP transfer across scale, showing fast transfer is equivalent to useful transfer for compute-optimal grid search.
result Fast transfer of hyperparameters is equivalent to useful transfer for compute-optimal grid search, offering asymptotic computational advantage.

We trace the initiative by Professor Meghnad Saha to develop a (statistical) physics model of market economy and his search for the mechanism to constrain the entropy maximized width of the income distribution in a society such that the spread of inequality can be minimized.

2018-08-28abs ↗pdf ↗

We introduce a new weight-decay scaling rule to maintain sublayer gains across different widths in modern scale-invariant architectures.

problem In modern scale-invariant architectures, training quickly enters a steady state where normalization layers create backward scale sensitivity, degrading learning-rate transfer.
method We introduce a weight-decay scaling rule for AdamW that preserves sublayer gain across widths by equalizing the effective learning rate.
result Our empirical weight-decay scaling rule λ2dλ_2\propto \sqrt{d} approximately keeps sublayer gains width invariant, enabling zero-shot transfer of learning rate and weight decay.

Large learning rates work surprisingly well in standard parameterization, contrary to theory.

problem Theoretical limits of large learning rates do not match practical network behavior.
method Fine-grained analysis of learning rates and network behavior under cross-entropy loss.
result There are two distinct sub-regimes of unstable learning rates, with a controlled divergence regime where features continue to evolve.

Semi-supervised clustering aims to introduce prior knowledge in the decision process of a clustering algorithm. In this paper, we propose a novel semi-supervised clustering algorithm based on the information-maximization principle. The proposed method is an extension of a previous unsupervised information-maximization …

2013-04-30abs ↗pdf ↗

New method μP2μP^2 improves neural network training by scaling perturbations layerwise.

problem Improving neural network performance as models scale up.
method Layerwise perturbation scaling in the infinite-width limit of neural networks.
result Layerwise perturbation scaling ensures all layers are effectively perturbed in the limit.

This paper shows how deep neural networks can learn rich, independent features that significantly deviate from initialization.

problem Understanding how deep neural networks achieve meaningful feature learning and global convergence.
method Investigation of infinitely wide, LL-layer neural networks using the tensor program framework under Maximal Update parametrization.
result SGD enables these networks to learn linearly independent features that substantially deviate from their initial values, capturing relevant data information.

We define the Wirtinger width of a knot. Then we prove the Wirtinger width of a knot equals its Gabai width. The algorithmic nature of the Wirtinger width leads to an efficient technique for establishing upper bounds on Gabai width. As an application, we use this technique to calculate the Gabai width of approximately …

2019-12-04abs ↗pdf ↗

Empirical study compares finite- and infinite-width BNNs, revealing performance differences under model mismatch.

problem Comparing BNNs with different widths due to conflicting model properties and inference intractability.
method Empirical comparison of finite- and infinite-width BNNs, analyzing performance under model mismatch.
result Increasing width can hurt BNN performance when the model is mis-specified, and finite-width BNNs generalize better under model mismatch.

Lectures on deep learning properties in infinite and large-width networks.

problem Understanding deep neural networks in extreme width conditions.
method Analysis of random deep neural networks, connections to linear models, kernels, and Gaussian processes, perturbative and non-perturbative treatments.
result Properties and behaviors of deep neural networks in the infinite-width limit and large-width regime.

A number of results for C2^2-smooth surfaces of constant width in Euclidean 3-space E3{\mathbb{E}}^3 are obtained. In particular, an integral inequality for constant width surfaces is established. This is used to prove that the ratio of volume to cubed width of a constant width surface is reduced by shrinking it along…

2007-04-24abs ↗pdf ↗

Residual networks with block width max(d_x, d_y) approximate all functions.

problem Achieving universal approximation with residual networks.
method Established bounds on block width for different activation functions.
result Minimum block width for universal approximation is max(d_x, d_y) with inner width 1.

While studying the existence of closed geodesics and minimal hypersurfaces in compact manifolds, the concept of width was introduced in different contexts. Generally, the width is realized by the energy of the closed geodesics or the volume of minimal hypersurfaces, which are found by the Minimax argument. Recently, Ma…

2016-12-20abs ↗pdf ↗

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.

In "Width complexes for knots and 3-manifolds," Jennifer Schultens defines the width complex for a knot in order to understand the different positions a knot can occupy in the 3-sphere and the isotopies between these positions. She poses several questions about these width complexes; in particular, she asks whether the…

2010-08-30abs ↗pdf ↗

RAmmStein optimizes liquidity management in AMMs by learning to rebalance efficiently.

problem Optimal control of concentrated liquidity in decentralized exchanges.
method Formulates as an optimal control problem, uses Deep Reinforcement Learning with HJB-QVI.
result Achieves highest net ROI (1.60%) compared to greedy strategies, reduces rebalancing frequency by 85%.

Gradient descent and SGD achieve low test error in specific network weight regimes.

problem Optimizing two-layer ReLU networks with standard initialization.
method Gradient flow and stochastic gradient descent, analyzing margins and weight norms.
result Gradient descent and SGD can achieve globally maximal margins under certain constraints.

We discuss a possible definition for "kk-width" of both a closed dd-manifold MdM^d, and on embedding MdeRnM^d \overset{e}{\hookrightarrow} \mathbb{R}^n, n>dkn > d \ge k, generalizing the classical notion of width of a knot. We show that for every 3-manifold 2-width(M3)2(M^3) \le 2 but that there are embeddings $e_i: T^3 \hoo…

2019-07-30abs ↗pdf ↗

We extend the classical definition of {\it width} to higher dimensional, smooth codimension 2 knots and show in each dimension there are knots of arbitrarily large width.

2019-02-19abs ↗pdf ↗