Search Results for author:
Found 10 papers, 2 papers with code
Structure-agnostic Optimality of Doubly Robust Learning for Treatment Effect Estimation
Average treatment effect estimation is the most central problem in causal inference with application to numerous disciplines.
Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking
Recent work by Power et al. (2022) highlighted a surprising "grokking" phenomenon in learning arithmetic tasks: a neural net first "memorizes" the training set, resulting in perfect training accuracy but near-random test accuracy, and after training for sufficiently longer, it suddenly transitions to perfect test accuracy.
Learning Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity
In this work, we provide the first identifiability results based on data that stem from general environments.
Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing
It is believed that Gradient Descent (GD) induces an implicit bias towards good generalization in training machine learning models.
Minimax Optimal Kernel Operator Learning via Multilevel Training
Learning mappings between infinite-dimensional function spaces has achieved empirical success in many disciplines of machine learning, including generative modeling, functional data analysis, causal inference, and multi-agent reinforcement learning.
Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power
Moreover, we establish an improved upper bound of $\exp({\mathcal{O}}(k))$ for the network size to achieve low robust generalization error when the data lies on a manifold with intrinsic dimension $k$ ($k \ll d$).
Understanding Riemannian Acceleration via a Proximal Extragradient Framework
We contribute to advancing the understanding of Riemannian accelerated gradient methods.
Non-convex Distributionally Robust Optimization: Non-asymptotic Analysis
Distributionally robust optimization (DRO) is a widely-used approach to learn models that are robust against distribution shift.
On The Convergence of First Order Methods for Quasar-Convex Optimization
Overall, this paper suggests that \textit{quasar-convexity} allows efficient optimization procedures, and we are looking forward to seeing more problems that demonstrate similar properties in practice.
Improved Analysis of Clipping Algorithms for Non-convex Optimization
Gradient clipping is commonly used in training deep neural networks partly due to its practicability in relieving the exploding gradient problem.
