Cover Image

HessFormer: Hessians at Foundation Scale

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Granziol, Diego
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Hessian Spectral Analysis at Foundation Model Scale
by: Granziol, Diego, et al.
Published: (2026)

Safety-Efficacy Trade Off: Robustness against Data-Poisoning
by: Granziol, Diego
Published: (2026)

A Linear Approach to Data Poisoning
by: Flynn, Donald, et al.
Published: (2025)

Hess-MC2: Sequential Monte Carlo Squared using Hessian Information and Second Order Proposals
by: Murphy, Joshua, et al.
Published: (2025)

Compute-Optimal LLMs Provably Generalize Better With Scale
by: Finzi, Marc, et al.
Published: (2025)

Universal characteristics of deep neural network loss surfaces from random matrix theory
by: Baskerville, Nicholas P, et al.
Published: (2022)

Connecting Parameter Magnitudes and Hessian Eigenspaces at Scale using Sketched Methods
by: Fernandez, Andres, et al.
Published: (2025)

TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
by: Wang, Haiyang, et al.
Published: (2024)

First-ish Order Methods: Hessian-aware Scalings of Gradient Descent
by: Smee, Oscar, et al.
Published: (2025)

Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision Making
by: Kim, Jeonghye, et al.
Published: (2023)

Hessian QM9: A quantum chemistry database of molecular Hessians in implicit solvents
by: Williams, Nicholas J., et al.
Published: (2024)

Depth, Not Data: An Analysis of Hessian Spectral Bifurcation
by: Deng, Shenyang, et al.
Published: (2026)

The Hessian of tall-skinny networks is easy to invert
by: Rahimi, Ali
Published: (2026)

Hessian-Informed Flow Matching
by: Sprague, Christopher Iliffe, et al.
Published: (2024)

E2Former: An Efficient and Equivariant Transformer with Linear-Scaling Tensor Products
by: Li, Yunyang, et al.
Published: (2025)

Bayesian Influence Functions for Hessian-Free Data Attribution
by: Kreer, Philipp Alexander, et al.
Published: (2025)

Neglected Hessian component explains mysteries in Sharpness regularization
by: Dauphin, Yann N., et al.
Published: (2024)

Revisit, Extend, and Enhance Hessian-Free Influence Functions
by: Yang, Ziao, et al.
Published: (2024)

scpFormer: A Foundation Model for Unified Representation and Integration of the Single-Cell Proteomics
by: Zhou, Qifeng, et al.
Published: (2026)

Hessian-Free Online Certified Unlearning
by: Qiao, Xinbao, et al.
Published: (2024)

Stochastic Hessian Fittings with Lie Groups
by: Li, Xi-Lin
Published: (2024)

Moment Alignment: Unifying Gradient and Hessian Matching for Domain Generalization
by: Chen, Yuen, et al.
Published: (2025)

A Hessian-informed hyperparameter optimization for differential learning rate
by: Xu, Shiyun, et al.
Published: (2025)

The Expected Loss of Preconditioned Langevin Dynamics Reveals the Hessian Rank
by: Bar, Amitay, et al.
Published: (2024)

Local Hessian Spectral Filtering for Robust Intrinsic Dimension Estimation
by: Osada, Genki
Published: (2026)

Revisiting inverse Hessian vector products for calculating influence functions
by: Klochkov, Yegor, et al.
Published: (2024)

Hessian Surgery: Class-Targeted Post-Hoc Rebalancing via Hessian Spike Perturbation
by: Vigna, Hugo, et al.
Published: (2026)

Community detection with the Bethe-Hessian
by: Stephan, Ludovic, et al.
Published: (2024)

Gradient-Normalized Smoothness for Optimization with Approximate Hessians
by: Semenov, Andrei, et al.
Published: (2025)

Towards Quantifying the Hessian Structure of Neural Networks
by: Dong, Zhaorui, et al.
Published: (2025)

Better Hessians Matter: Studying the Impact of Curvature Approximations in Influence Functions
by: Hong, Steve, et al.
Published: (2025)

Unraveling the Hessian: A Key to Smooth Convergence in Loss Function Landscapes
by: Kiselev, Nikita, et al.
Published: (2024)

Foundation Models for Clinical Records at Health System Scale
by: Rajamohan, Haresh Rengaraj, et al.
Published: (2025)

Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy Hessians
by: Amin, Ishan, et al.
Published: (2025)

TeamFormer: Shallow Parallel Transformers with Progressive Approximation
by: Wang, Wei, et al.
Published: (2025)

RiemannFormer: A Framework for Attention in Curved Spaces
by: Ji, Zhongping
Published: (2025)

CogFormer: Learn All Your Models Once
by: Huang, Jerry M., et al.
Published: (2026)

CycleFormer : TSP Solver Based on Language Modeling
by: Yook, Jieun, et al.
Published: (2024)

WaveFormer: Wavelet Embedding Transformer for Biomedical Signals
by: Irani, Habib, et al.
Published: (2026)

Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection
by: Xu, Shiyun, et al.
Published: (2025)