39 citations · 101 across the 17 of their papers we have counts for
17 papers
Leveraging Contextual Counterfactuals Toward Belief Calibration
Qiuyi, Zhang, Michael S. Lee +1
Beliefs and values are increasingly being incorporated into our AI systems through alignment processes, such as carefully curating data collection principles or regularizing the lo…
Set Learning for Accurate and Calibrated Models
Lukas Muttenthaler, Robert A. Vandermeulen, Qiuyi Zhang +2
Model overconfidence and poor calibration are common in machine learning and difficult to account for when applying standard empirical risk minimization. In this work, we propose a…
Robust Algorithms on Adaptive Inputs from Bounded Adversaries
Yeshwanth Cherapanamjeri, Sandeep Silwal, David P. Woodruff +3
We study dynamic algorithms robust to adaptive input generated from sources with bounded capabilities, such as sparsity or limited interaction. For example, we consider robust line…
Optimal Query Complexities for Dynamic Trace Estimation
David P. Woodruff, Fred Zhang, Qiuyi Zhang
We consider the problem of minimizing the number of matrix-vector queries needed for accurate trace estimation in the dynamic setting where our underlying matrix is changing slowly…
Towards Learning Universal Hyperparameter Optimizers with Transformers
Yutian Chen, Xingyou Song, Chansoo Lee +9
Meta-learning hyperparameter optimization (HPO) algorithms from prior experiments is a promising approach to improve optimization efficiency over objective functions from a similar…
Leveraging Initial Hints for Free in Stochastic Linear Bandits
Ashok Cutkosky, Chris Dann, Abhimanyu Das +2
We study the setting of optimizing with bandit feedback with additional prior knowledge provided to the learner in the form of an initial hint of the optimal action. We present a n…
Optimal Sketching for Trace Estimation
Shuli Jiang, Hai Pham, David P. Woodruff +2
Matrix trace estimation is ubiquitous in machine learning applications and has traditionally relied on Hutchinson's method, which requires matrix-vector product…
One Network Fits All? Modular versus Monolithic Task Formulations in Neural Networks
Atish Agarwala, Abhimanyu Das, Brendan Juba +4
Can deep learning solve multiple tasks simultaneously, even when they are unrelated and very different? We investigate how the representations of the underlying tasks affect the ab…
ES-ENAS: Efficient Evolutionary Optimization for Large Hybrid Search Spaces
Xingyou Song, Krzysztof Choromanski, Jack Parker-Holder +8
In this paper, we approach the problem of optimizing blackbox functions over large hybrid search spaces consisting of both combinatorial and continuous parameters. We demonstrate t…
Random Hypervolume Scalarizations for Provable Multi-Objective Black Box Optimization
Daniel Golovin, Qiuyi Zhang
Single-objective black box optimization (also known as zeroth-order optimization) is the process of minimizing a scalar objective , given evaluations at adaptively chosen inp…
Learning the gravitational force law and other analytic functions
Atish Agarwala, Abhimanyu Das, Rina Panigrahy +1
Large neural network models have been successful in learning functions of importance in many branches of science, including physics, chemistry and biology. Recent theoretical work…
Span Recovery for Deep Neural Networks with Applications to Input Obfuscation
Rajesh Jayaram, David P. Woodruff, Qiuyi Zhang
The tremendous success of deep neural networks has motivated the need to better understand the fundamental properties of these networks, but many of the theoretical results propose…
Regularized Weighted Low Rank Approximation
Frank Ban, David Woodruff, Qiuyi Zhang
The classical low rank approximation problem is to find a rank matrix (where has columns and has rows) that minimizes the Frobenius norm of . Altho…
Gradientless Descent: High-Dimensional Zeroth-Order Optimization
Daniel Golovin, John Karro, Greg Kochanski +3
Zeroth-order optimization is the process of minimizing an objective , given oracle access to evaluations at adaptively chosen inputs . In this paper, we present two simple…
Solving Empirical Risk Minimization in the Current Matrix Multiplication Time
Yin Tat Lee, Zhao Song, Qiuyi Zhang
Many convex problems in machine learning and computer science share the same form: \begin{align*} \min_{x} \sum_{i} f_i( A_i x + b_i), \end{align*} where are convex functions…
Optimal Sequence Length Requirements for Phylogenetic Tree Reconstruction with Indels
Arun Ganesh, Qiuyi Zhang
We consider the phylogenetic tree reconstruction problem with insertions and deletions (indels). Phylogenetic algorithms proceed under a model where sequences evolve down the model…
Convergence Results for Neural Networks via Electrodynamics
Rina Panigrahy, Sushant Sachdeva, Qiuyi Zhang
We study whether a depth two neural network can learn another depth two network using gradient descent. Assuming a linear output node, we show that the question of whether gradient…