paper-with-me

Papers

From Low Intrinsic Dimensionality to Non-Vacuous Generalization Bounds in Deep Multi-Task Learning

2025-01-31 · Hossein Zakerinia, Dorsa Ghobadi, Christoph H. Lampert

Deep learning methods are known to generalize well from training to future data, even in an overparametrized regime, where they could easily overfit. One explanation for this phenomenon is that even when their *ambient dimensionality*, (i.e. the number of parameters) is large, the models' *intrinsic dimensionality* is small; specifically, their learning takes place in a small subspace of all possible weight configurations. In this work, we confirm this phenomenon in the setting of *deep multi-task learning*. We introduce a method to parametrize multi-task network directly in the low-dimensional space, facilitated by the use of *random expansions* techniques. We then show that high-accuracy multi-task solutions can be found with much smaller intrinsic dimensionality (fewer free parameters) than what single-task learning requires. Subsequently, we show that the low-dimensional representations in combination with *weight compression* and *PAC-Bayesian* reasoning lead to the *first non-vacuous generalization bounds* for deep multi-task networks.

📄 PDF Abstract BibTeX arXiv:2501.19067

Code (1)

hzakerinia/mtl 공식 구현 pytorch

Tasks

Generalization BoundsMulti-Task Learning

Similar Papers 제목 키워드 기반

PAC-Bayesian Generalization Bounds for Adversarial Generative Models

2023-02-17 · Sokhna Diarra Mbacke, Florence Clerc, Pascal Germain

We extend PAC-Bayesian theory to generative models and develop generalization bounds for models based on the Wasserstein distance and the total variation distance. Our first result on the Wasserstein distance assumes the…

Dimensionality ReductionGeneralization Bounds

A Generalization Bound for Nearly-Linear Networks

2024-07-09 · Eugene Golikov

We consider nonlinear networks as perturbations of linear ones. Based on this approach, we present novel generalization bounds that become non-vacuous for networks that are close to being linear. The main advantage over …

Generalization Bounds

Non-Vacuous Generalization Bounds for Large Language Models

2023-12-28 · Sanae Lotfi, Marc Finzi, Yilun Kuang, Tim G. J. Rudner 외

Modern language models can contain billions of parameters, raising the question of whether they can generalize beyond the training data or simply parrot their training corpora. We provide the first non-vacuous generaliza…

Generalization Boundsvalid

Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data

2017-03-31 · Gintare Karolina Dziugaite, Daniel M. Roy

One of the defining properties of deep learning is that models are chosen to have many more parameters than available training data. In light of this capacity for overfitting, it is remarkable that simple algorithms like…

Generalization Bounds

Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models

2024-07-25 · Sanae Lotfi, Yilun Kuang, Brandon Amos, Micah Goldblum 외

Large language models (LLMs) with billions of parameters excel at predicting the next token in a sequence. Recent work computes non-vacuous compression-based generalization bounds for LLMs, but these bounds are vacuous f…

Generalization BoundsQuantization