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.
Guarantees for tuning step size using meta-gradient descent.
Meta-gradient RL learns to learn from experience.
Representations are fundamental to artificial intelligence. The performance of a learning system depends on the type of representation used for representing the data. Typically, these representations are hand-engineered using domain knowledge. More recently, the trend is to learn these representations through stochasti…
Meta-gradient D4PG optimizes performance and constraint adherence in RL.
This paper investigates different vector step-size adaptation approaches for non-stationary online, continual prediction problems. Vanilla stochastic gradient descent can be considerably improved by scaling the update with a vector of appropriately chosen step-sizes. Many methods, including AdaGrad, RMSProp, and AMSGra…
Evolutionary Strategies optimize hyper-parameters for off-policy learning.
Reinforcement learning (RL) has had many successes in both "deep" and "shallow" settings. In both cases, significant hyperparameter tuning is often required to achieve good performance. Furthermore, when nonlinear function approximation is used, non-stationarity in the state representation can lead to learning instabil…
Proposes a meta-learning algorithm to improve semi-supervised learning.
Learning an efficient update rule from data that promotes rapid learning of new tasks from the same distribution remains an open problem in meta-learning. Typically, previous works have approached this issue either by attempting to train a neural network that directly produces updates or by attempting to learn better i…
Synthetic data helps prevent forgetting when learning sequentially.
Accelerates policy optimization in RL with optimistic and adaptive updates.
MSLG generates soft labels to improve DNN performance on noisy datasets.
Deep neural networks have been shown to be very powerful modeling tools for many supervised learning tasks involving complex input patterns. However, they can also easily overfit to training set biases and label noises. In addition to various regularizers, example reweighting algorithms are popular solutions to these p…
AdvImmune improves certifiable robustness of GNNs against adversarial attacks.
Reinforcement learning algorithms are highly sensitive to the choice of hyperparameters, typically requiring significant manual effort to identify hyperparameters that perform well on a new domain. In this paper, we take a step towards addressing this issue by using metagradients to automatically adapt hyperparameters …
A core capability of intelligent systems is the ability to quickly learn new tasks by drawing on prior experience. Gradient (or optimization) based meta-learning has recently emerged as an effective approach for few-shot learning. In this formulation, meta-parameters are learned in the outer loop, while task-specific m…
Deep learning models for graphs have advanced the state of the art on many tasks. Despite their recent success, little is known about their robustness. We investigate training time attacks on graph neural networks for node classification that perturb the discrete graph structure. Our core principle is to use meta-gradi…
In few-shot learning, typically, the loss function which is applied at test time is the one we are ultimately interested in minimising, such as the mean-squared-error loss for a regression problem. However, given that we have few samples at test time, we argue that the loss function that we are interested in minimising…
Improves meta-learning efficiency with mixed-mode differentiation.
DataRater learns which data points are most valuable for training models.
The goal of reinforcement learning algorithms is to estimate and/or optimise the value function. However, unlike supervised learning, no teacher or oracle is available to provide the true value function. Instead, the majority of reinforcement learning algorithms estimate and/or optimise a proxy for the value function. …
MetAL improves graph classification models with fewer labeled data.
New algorithm improves dataset distillation with 108% improvement on ImageNet.
As a popular meta-learning approach, the model-agnostic meta-learning (MAML) algorithm has been widely used due to its simplicity and effectiveness. However, the convergence of the general multi-step MAML still remains unexplored. In this paper, we develop a new theoretical framework to provide such convergence guarant…
New method optimises learning via surrogate PAC-Bayes bounds.
Improved learning to reweight using deep interactions between student and teacher models.
Blind Descent avoids gradient issues, using a different learning approach.
G-Meta learns graph meta-learning from local subgraphs.
Derives Mirror Descent from gradient flow on a Riemannian manifold.
Accelerates coordinate descent methods for machine learning problems.
Stochastic gradient descent on manifolds improves low-rank approximation.
In this note, we observe the behavior of gradient flow and discrete and noisy gradient descent in some simple settings. It is commonly noted that addition of noise to gradient descent can affect the trajectory of gradient descent. Here, we run some computer experiments for gradient descent on some simple functions, and…
Most of the recent successful applications of neural networks have been based on training with gradient descent updates. However, for some small networks, other mirror descent updates learn provably more efficiently when the target is sparse. We present a general framework for casting a mirror descent update as a gradi…
New analysis shows GMD can converge linearly under PL-like conditions.
A new method improves stochastic gradient descent for faster and more efficient estimation.
Double descent phenomenon explained in simple terms.
New adaptive step-size method for convex optimization without tuning.
New insights into double descent phenomenon in neural networks.
Gradient descent dynamics in nonconvex models explained with universality.
Gradient descent variants improve phase retrieval accuracy.
The paper connects tempering and entropic mirror descent for sampling.
We consider the behavior of gradient flow and of discrete and noisy gradient descent. It is commonly noted that the addition of noise to the process of discrete gradient descent can affect the trajectory of gradient descent. In previous work, we observed such effects. There, we considered the case where the minima had …
Develops DP-SCD for stochastic coordinate descent, making it differentially private.
Information geometry applies concepts in differential geometry to probability and statistics and is especially useful for parameter estimation in exponential families where parameters are known to lie on a Riemannian manifold. Connections between the geometric properties of the induced manifold and statistical properti…
Paper uses Mirror Descent for efficient risk budgeting portfolios.
Any gradient descent optimization requires to choose a learning rate. With deeper and deeper models, tuning that learning rate can easily become tedious and does not necessarily lead to an ideal convergence. We propose a variation of the gradient descent algorithm in the which the learning rate is not fixed. Instead, w…
In this paper we elaborate a general homotopy-theoretic framework in which to study problems of descent and completion and of their duals, codescent and cocompletion. Our approach to homotopic (co)descent and to derived (co)completion can be viewed as -category-theoretic, as our framework is constructed in the …
This paper explains why double descent sometimes occurs weakly or not at all from an optimization perspective.