Search Results for author:
Found 19 papers, 6 papers with code
Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning
Sharpness-Aware Minimization (SAM) has emerged as a promising alternative optimizer to stochastic gradient descent (SGD).
The pitfalls of next-token prediction
The popular criticism that errors can compound during autoregressive inference, crucially assumes that teacher-forcing has learned an accurate next-token predictor.
What do larger image classifiers memorise?
The success of modern neural networks has prompted study of the connection between memorisation and generalisation: overparameterised models generalise well, despite being able to perfectly fit (memorise) completely random labels.
The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning
We study two natural scaling techniques -- weight pruning and simply training a smaller or larger model, which we refer to as dense scaling -- and their effects on two core capabilities of LLMs: (a) recalling facts presented during pre-training and (b) processing information presented in-context during inference.
Think before you speak: Training Language Models With Pause Tokens
Language models generate responses by producing a series of tokens in immediate succession: the $(K+1)^{th}$ token is an outcome of manipulating $K$ hidden vectors per layer, one vector per preceding token.
On student-teacher deviations in distillation: does it pay to disobey?
Knowledge distillation (KD) has been widely used to improve the test accuracy of a "student" network, by training it to mimic the soft probabilities of a trained "teacher" network.
Explaining generalization in deep learning: progress and fundamental limits
This dissertation studies a fundamental open challenge in deep learning theory: why do deep networks generalize well even while being overparameterized, unregularized and fitting the training data to zero error?
Assessing Generalization of SGD via Disagreement
We empirically show that the test error of deep networks can be estimated by simply training the same architecture on the same training set but with a different run of Stochastic Gradient Descent (SGD), and measuring the disagreement rate between the two networks on unlabeled test data.
A Learning Theoretic Perspective on Local Explainability
In this paper, we explore connections between interpretable machine learning and learning theory through the lens of local approximation explanations.
BIG-bench Machine Learning
Interpretable Machine Learning
+1
Understanding the Failure Modes of Out-of-Distribution Generalization
Empirical studies suggest that machine learning models often rely on features, such as the background, that may be spuriously correlated with the label only during training time, resulting in poor accuracy during test-time.
Provably Safe PAC-MDP Exploration Using Analogies
A key challenge in applying reinforcement learning to safety-critical domains is understanding how to balance exploration (needed to attain good performance on the task) with safety (needed to avoid catastrophic failure).
Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience
The ability of overparameterized deep networks to generalize well has been linked to the fact that stochastic gradient descent (SGD) finds solutions that lie in flat, wide minima in the training loss -- minima where the output of the network is resilient to small random noise added to its parameters.
Uniform convergence may be unable to explain generalization in deep learning
Aimed at explaining the surprisingly good generalization behavior of overparameterized deep networks, recent works have developed a variety of generalization bounds for deep learning, all based on the fundamental learning-theoretic technique of uniform convergence.
Generalization in Deep Networks: The Role of Distance from Initialization
Why does training deep neural networks using stochastic gradient descent (SGD) result in a generalization error that does not worsen with the number of parameters in the network?
Revisiting Adversarial Risk
Based on the modified definition, we show that there is no trade-off between adversarial and standard accuracies; there exist classifiers that are robust and achieve high standard accuracy.
Lifelong Learning in Costly Feature Spaces
An important long-term goal in machine learning systems is to build learning agents that, like humans, can learn many tasks over their lifetime, and moreover use information from these tasks to improve their ability to do so efficiently.
Gradient descent GAN optimization is locally stable
Despite the growing prominence of generative adversarial networks (GANs), optimization in GANs is still a poorly understood topic.
Learning-Theoretic Foundations of Algorithm Configuration for Combinatorial Partitioning Problems
We address this problem for clustering, max-cut, and other partitioning problems, such as integer quadratic programming, by designing computationally efficient and sample efficient learning algorithms which receive samples from an application-specific distribution over problem instances and learn a partitioning algorithm with high expected performance.
A Reinforcement Learning Approach to Online Learning of Decision Trees
Online decision tree learning algorithms typically examine all features of a new data point to update model parameters.
