MétaCan
Menu
Back to cohort
Record W7133004520

Optimization and Loss Landscape Geometry of Deep Learning

2022· dissertation· W7133004520 on OpenAlexaff
James Robert Lucas

Bibliographic record

VenueTSpace · 2022
Typedissertation
Language
FieldComputer Science
TopicStochastic Gradient Optimization Techniques
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsDeep learningArtificial neural networkDeep neural networksSet (abstract data type)Class (philosophy)Convolutional neural networkOptimization problemFocus (optics)
DOInot available

Abstract

fetched live from OpenAlex

The impressive success of deep learning is powered by models that are rapidly growing in size along with the computational resources that are used to train them. Despite these growing demands, the dominant tools used to train these networks have not evolved significantly to match these needs. One natural hypothesis for this limitation is our lack of understanding of the training dynamics of deep neural networks. In this thesis, I present our research on understanding and improving the optimization of deep learning models. The thesis begins by presenting two first-order optimization algorithms for deep learning: the Aggregated Momentum and Lookahead optimizers. We demonstrate their success on modern deep learning optimization problems and provide theoretical analyses of both optimizers in convex settings. However, our theoretical understanding of optimization for practical training of deep neural networks is severely limited. Following this, we turn towards building a better understanding of deep learning optimization. We achieve this by studying the loss landscape geometry of deep neural networks. This is extremely challenging due to non-convex objective functions and extremely high-dimensional parameter spaces. We address this by first studying a simple class of neural networks: two-layer linear networks. Despite their simplicity, these models capture some core challenges of deep learning optimization effectively. Within this class, we investigate regularized linear autoencoders and linear variational autoencoders and carefully characterize their loss landscape geometry theoretically. We then move beyond the simple class of two-layer linear networks to investigate a phenomenon that arises across a vast set of deep learning optimization problems. This phenomenon, which we term the Monotonic Linear Interpolation (MLI) property, describes a global property of the loss landscape geometry of deep learning models. We provide the first theoretical explanation of this phenomenon and conduct a thorough empirical investigation to better understand the pervasiveness and limitations of the MLI property. In the final chapter, the thesis is discussed as a whole and promising directions for future research are presented.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.006
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.003
Threshold uncertainty score0.012

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.006
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.000
Science and technology studies0.0000.002
Scholarly communication0.0020.003
Open science0.0010.002
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0030.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.010
GPT teacher head0.290
Teacher spread0.280 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2022
Admission routes1
Has abstractyes

Explore more

Same venueTSpaceSame topicStochastic Gradient Optimization TechniquesFrench-language works237,207