Search Results for author:
Found 19 papers, 12 papers with code
On the Iteration Complexity of Hypergradient Computations
We study a general class of bilevel optimization problems, in which the upper-level objective is defined via the solution of a fixed point equation.
CoRet: Improved Retriever for Code Editing
In this paper, we introduce CoRet, a dense retrieval model designed for code-editing tasks that integrates code semantics, repository structure, and call graph dependencies.
Hyperparameter Optimization in Machine Learning
Hyperparameters are configuration variables controlling the behavior of machine learning algorithms.
Jet Expansions of Residual Computation
We introduce a framework for expanding residual computational graphs using jets, operators that generalize truncated Taylor series.
Evaluating Large Language Models with fmeval
A case study demonstrates a typical use case for the library: picking a suitable model for a question answering task.
Explaining Probabilistic Models with Distributional Values
We argue that often there is a critical mismatch between what one wishes to explain (e. g. the output of a classifier) and what current methods such as SHAP explain (e. g. the scalar probability of a class).
DAG Learning on the Permutahedron
We propose a continuous optimization framework for discovering a latent directed acyclic graph (DAG) from observational data.
Learning Discrete Directed Acyclic Graphs via Backpropagation
Recently continuous relaxations have been proposed in order to learn Directed Acyclic Graphs (DAGs) from data by backpropagation, instead of using combinatorial optimization.
Adaptive Perturbation-Based Gradient Estimation for Discrete Latent Variable Models
In this work, we present Adaptive IMLE (AIMLE), the first adaptive gradient estimator for complex discrete distributions: it adaptively identifies the target distribution for IMLE by trading off the density of gradient information with the degree of bias in the gradient estimates.
ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective
Factorisation-based Models (FMs), such as DistMult, have enjoyed enduring success for Knowledge Graph Completion (KGC) tasks, often outperforming Graph Neural Networks (GNNs).
Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions
We propose Implicit Maximum Likelihood Estimation (I-MLE), a framework for end-to-end learning of models combining discrete exponential family distributions and differentiable neural components.
On the Iteration Complexity of Hypergradient Computation
We study a general class of bilevel problems, consisting in the minimization of an upper-level objective which depends on the solution to a parametric fixed-point equation.
MARTHE: Scheduling the Learning Rate Via Online Hypergradients
We study the problem of fitting task-specific learning rate schedules from the perspective of hyperparameter optimization, aiming at good generalization.
Scheduling the Learning Rate Via Hypergradients: New Insights and a New Algorithm
We study the problem of fitting task-specific learning rate schedules from the perspective of hyperparameter optimization.
Learning Discrete Structures for Graph Neural Networks
With this work, we propose to jointly learn the graph structure and the parameters of graph convolutional networks (GCNs) by approximately solving a bilevel program that learns a discrete probability distribution on the edges of the graph.
Ranked #3 on
Node Classification
on Cora: fixed 20 node per class
Far-HO: A Bilevel Programming Package for Hyperparameter Optimization and Meta-Learning
In (Franceschi et al., 2018) we proposed a unified mathematical framework, grounded on bilevel programming, that encompasses gradient-based hyperparameter optimization and meta-learning.
Bilevel Programming for Hyperparameter Optimization and Meta-Learning
We introduce a framework based on bilevel programming that unifies gradient-based hyperparameter optimization and meta-learning.
A Bridge Between Hyperparameter Optimization and Learning-to-learn
We consider a class of a nested optimization problems involving inner and outer objectives.
Forward and Reverse Gradient-Based Hyperparameter Optimization
We study two procedures (reverse-mode and forward-mode) for computing the gradient of the validation error with respect to the hyperparameters of any iterative learning algorithm such as stochastic gradient descent.
