Publications (123)
On the proliferation of support vectors in high dimensions
Daniel Hsu, Vidya Muthukumar, Ji Xu
The support vector machine (SVM) is a well-established classification method whose name refers to the particular training examples, called support vectors, that determine the maxim…
The price of multi-group transductive learning
Noah Bergam, Samuel Deng, Daniel Hsu
We show every multi-group learner in the transductive setting may incur a multiplicative penalty in its error rate on some group relative to the error rate achievable in the single…
Diameter-based Interactive Structure Discovery
Christopher Tosh, Daniel Hsu
We introduce interactive structure discovery, a generic framework that encompasses many interactive learning settings, including active learning, top-k item identification, interac…
Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate
Mikhail Belkin, Daniel Hsu, Partha Mitra
Many modern machine learning models are trained to achieve zero or near-zero training error in order to obtain near-optimal (but non-zero) test error. This phenomenon of strong gen…
Cross-Lingual Text Classification with Minimal Resources by Transferring a Sparse Teacher
Giannis Karamanolakis, Daniel Hsu, Luis Gravano
Cross-lingual text classification alleviates the need for manually labeled documents in a target language by leveraging labeled documents from other languages. Existing approaches…
FairTest: Discovering Unwarranted Associations in Data-Driven Applications
Florian Tramèr, Vaggelis Atlidakis, Roxana Geambasu +5
In a world where traditional notions of privacy are increasingly challenged by the myriad companies that collect and analyze our data, it is important that decision-making entities…
Group-wise oracle-efficient algorithms for online multi-group learning
Samuel Deng, Daniel Hsu, Jingwen Liu
We study the problem of online multi-group learning, a learning model in which an online learner must simultaneously achieve small prediction regret on a large collection of (possi…
Group-realizable multi-group learning by minimizing empirical risk
Navid Ardeshir, Samuel Deng, Daniel Hsu +1
The sample complexity of multi-group learning is shown to improve in the group-realizable setting over the agnostic setting, even when the family of groups is infinite so long as i…
Near-Optimal Statistical Query Lower Bounds for Agnostically Learning Intersections of Halfspaces with Gaussian Marginals
Daniel Hsu, Clayton Sanford, Rocco Servedio +1
We consider the well-studied problem of learning intersections of halfspaces under the Gaussian distribution in the challenging \emph{agnostic learning} model. Recent work of Diako…
A parameter-free hedging algorithm
Kamalika Chaudhuri, Yoav Freund, Daniel Hsu
We study the problem of decision-theoretic online learning (DTOL). Motivated by practical applications, we focus on DTOL when the number of actions is very large. Previous algorith…
Stochastic convex optimization with bandit feedback
Alekh Agarwal, Dean P. Foster, Daniel Hsu +2
This paper addresses the problem of minimizing a convex, Lipschitz function over a convex, compact set $\xset$ under a stochastic bandit feedback model. In this model, the algo…
A Study on the Performance of U-Net Modifications in Retroperitoneal Tumor Segmentation
Moein Heidari, Ehsan Khodapanah Aghdam, Alexander Manzella +5
The retroperitoneum hosts a variety of tumors, including rare benign and malignant types, which pose diagnostic and treatment challenges due to their infrequency and proximity to v…
A concentration theorem for projections
Sanjoy Dasgupta, Daniel Hsu, Nakul Verma
X in R^D has mean zero and finite second moments. We show that there is a precise sense in which almost all linear projections of X into R^d (for d < D) look like a scale-mixture o…
One-layer transformers fail to solve the induction heads task
Clayton Sanford, Daniel Hsu, Matus Telgarsky
A simple communication complexity argument proves that no one-layer transformer can solve the induction heads task unless its size is exponentially larger than the size sufficient…
Learning Gaussian Multi-Index Models with Gradient Flow: Time Complexity and Directional Convergence
Berfin ÅimÅek, Amire Bendjeddou, Daniel Hsu
This work focuses on the gradient flow dynamics of a neural network model that uses correlation loss to approximate a multi-index function on high-dimensional standard Gaussian dat…
Simple and near-optimal algorithms for hidden stratification and multi-group learning
Christopher Tosh, Daniel Hsu
Multi-group agnostic learning is a formal learning criterion that is concerned with the conditional risks of predictors within subgroups of a population. The criterion addresses re…
Support vector machines and linear regression coincide with very high-dimensional features
Navid Ardeshir, Clayton Sanford, Daniel Hsu
The support vector machine (SVM) and minimum Euclidean norm least squares regression are two fundamentally different approaches to fitting linear models, but they have recently bee…
Parameter identification in Markov chain choice models
Arushi Gupta, Daniel Hsu
This work studies the parameter identification problem for the Markov chain choice model of Blanchet, Gallego, and Goyal used in assortment planning. In this model, the product sel…
Weak lensing cosmology with convolutional neural networks on noisy data
DezsÅ Ribli, Bálint Ãrmin Pataki, José Manuel Zorrilla Matilla +3
Weak gravitational lensing is one of the most promising cosmological probes of the late universe. Several large ongoing (DES, KiDS, HSC) and planned (LSST, EUCLID, WFIRST) astronom…
Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot
Zixuan Wang, Stanley Wei, Daniel Hsu +1
The transformer architecture has prevailed in various deep learning settings due to its exceptional capabilities to select and compose structural information. Motivated by these ca…
Dimension-free tail inequalities for sums of random matrices
Daniel Hsu, Sham M. Kakade, Tong Zhang
We derive exponential tail inequalities for sums of random matrices with no dependence on the explicit matrix dimensions. These are similar to the matrix versions of the Chernoff b…
Robust Matrix Decomposition with Outliers
Daniel Hsu, Sham M. Kakade, Tong Zhang
Suppose a given observation matrix can be decomposed as the sum of a low-rank matrix and a sparse matrix (outliers), and the goal is to recover these individual components from the…
Fast Matrix Multiplication with Sketching
Huan Wang, Christos Boutsidis, Edo Liberty +1
We present an approximate algorithm for matrix multiplication based on matrix sketching techniques. First one of the matrix is chosen and sparsified using the online matrix sketchi…
Fixed Universal Transformers
Jingwen Liu, Alexandr Andoni, Daniel Hsu
We introduce \emph{universal transformers}: fixed transformers that can simulate any transformer in a given class via a suitable input embedding. Analogous to a universal Turing ma…
ShakyPrepend: A Multi-Group Learner with Improved Sample Complexity
Lujing Zhang, Daniel Hsu, Sivaraman Balakrishnan
Multi-group learning is a learning task that focuses on controlling predictors' conditional losses over specified subgroups. We propose ShakyPrepend, a method that leverages tools…
Masked prediction tasks: a parameter identifiability view
Bingbin Liu, Daniel Hsu, Pradeep Ravikumar +1
The vast majority of work in self-supervised learning, both theoretical and empirical (though mostly the latter), have largely focused on recovering good features for downstream ta…
Generalization bounds via distillation
Daniel Hsu, Ziwei Ji, Matus Telgarsky +1
This paper theoretically investigates the following empirical phenomenon: given a high-complexity network with poor generalization bounds, one can distill it into a network with ne…
A Spectral Algorithm for Learning Hidden Markov Models
Daniel Hsu, Sham M. Kakade, Tong Zhang
Hidden Markov Models (HMMs) are one of the most fundamental and widely used statistical tools for modeling discrete time series. In general, learning HMMs from data is computationa…
Benefits of over-parameterization with EM
Ji Xu, Daniel Hsu, Arian Maleki
Expectation Maximization (EM) is among the most popular algorithms for maximum likelihood estimation, but it is generally only guaranteed to find its stationary points of the log-l…
Convergence Rates for Differentially Private Statistical Estimation
Kamalika Chaudhuri, Daniel Hsu
Differential privacy is a cryptographically-motivated definition of privacy which has gained significant attention over the past few years. Differentially private solutions enforce…
Contrastive learning, multi-view redundancy, and linear models
Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu
Self-supervised learning is an empirically successful approach to unsupervised learning based on creating artificial supervised learning problems. A popular self-supervised approac…
Kernel Approximation Methods for Speech Recognition
Avner May, Alireza Bagheri Garakani, Zhiyun Lu +9
We study large-scale kernel methods for acoustic modeling in speech recognition and compare their performance to deep neural networks (DNNs). We perform experiments on four speech…
Search Improves Label for Active Learning
Alina Beygelzimer, Daniel Hsu, John Langford +1
We investigate active learning with access to two distinct oracles: Label (which is standard) and Search (which is not). The Search oracle models the situation where a human search…
The Large Margin Mechanism for Differentially Private Maximization
Kamalika Chaudhuri, Daniel Hsu, Shuang Song
A basic problem in the design of privacy-preserving algorithms is the private maximization problem: the goal is to pick an item from a universe that (approximately) maximizes a dat…
Distribution-Specific Auditing For Subgroup Fairness
Daniel Hsu, Jizhou Huang, Brendan Juba
We study the problem of auditing classifiers with the notion of statistical subgroup fairness. Kearns et al. (2018) has shown that the problem of auditing combinatorial subgroups f…
Classification vs regression in overparameterized regimes: Does the loss function matter?
Vidya Muthukumar, Adhyyan Narang, Vignesh Subramanian +3
We compare classification and regression tasks in an overparameterized linear model with Gaussian features. On the one hand, we show that with sufficient overparameterization all t…
Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback
Ved Sriraman, Peihan Liu, Daniel Hsu +1
Imitation Learning is a natural framework for learning in sequential decision-making systems and has emerged as the dominant paradigm through which we understand language model tra…
Attention-based representations for multi-task computation
Daniel Hsu, Mingyue Xu
Multi-head attention layers produce vector representations that support multiple downstream tasks. We establish bounds on the number of heads required in two simple and concrete mu…
Privacy Accounting and Quality Control in the Sage Differentially Private ML Platform
Mathias Lecuyer, Riley Spahn, Kiran Vodrahalli +2
Companies increasingly expose machine learning (ML) models trained over sensitive user data to untrusted domains, such as end-user devices and wide-access model stores. We present…
Multi-Label Prediction via Compressed Sensing
Daniel Hsu, Sham M. Kakade, John Langford +1
We consider multi-label prediction problems with large output spaces under the assumption of output sparsity -- that the target (label) vectors have small support. We develop a gen…
On the number of variables to use in principal component regression
Ji Xu, Daniel Hsu
We study least squares linear regression over uncorrelated Gaussian features that are selected in order of decreasing variance. When the number of selected features is at m…
An Online Learning-based Framework for Tracking
Kamalika Chaudhuri, Yoav Freund, Daniel Hsu
We study the tracking problem, namely, estimating the hidden state of an object over time, from unreliable and noisy measurements. The standard framework for the tracking problem i…
The piranha problem: Large effects swimming in a small pond
Christopher Tosh, Philip Greengard, Ben Goodrich +3
In some scientific fields, it is common to have certain variables of interest that are of particular importance and for which there are many studies indicating a relationship with…
Efficient Optimal Learning for Contextual Bandits
Miroslav Dudik, Daniel Hsu, Satyen Kale +4
We address the problem of learning in an online setting where the learner repeatedly observes features, selects among a set of actions, and receives reward for the action taken. We…
Lower bounds for one-layer transformers that compute parity
Daniel Hsu
This note shows that no self-attention layer post-processed by a rational function can sign-represent the parity function unless the product of the number of heads and the degree o…
A tail inequality for quadratic forms of subgaussian random vectors
Daniel Hsu, Sham M. Kakade, Tong Zhang
We prove an exponential probability tail inequality for positive semidefinite quadratic forms in a subgaussian random vector. The bound is analogous to one that holds when the vect…
Time Series Compression Based on Adaptive Piecewise Recurrent Autoencoder
Daniel Hsu
Time series account for a large proportion of the data stored in financial, medical and scientific databases. The efficient storage of time series is important in practical applica…
A Method of Moments for Mixture Models and Hidden Markov Models
Animashree Anandkumar, Daniel Hsu, Sham M. Kakade
Mixture models are a fundamental tool in applied statistics and machine learning for treating data taken from multiple subpopulations. The current practice for estimating the param…
Certified Robustness to Adversarial Examples with Differential Privacy
Mathias Lecuyer, Vaggelis Atlidakis, Roxana Geambasu +2
Adversarial examples that fool machine learning models, particularly deep neural networks, have been a topic of intense research interest, with attacks and defenses being developed…
Fast attention mechanisms: a tale of parallelism
Jingwen Liu, Hantao Yu, Clayton Sanford +2
Transformers have the representational capacity to simulate Massively Parallel Computation (MPC) algorithms, but they suffer from quadratic time complexity, which severely limits t…
Representational Strengths and Limitations of Transformers
Clayton Sanford, Daniel Hsu, Matus Telgarsky
Attention layers, as commonly used in transformers, form the backbone of modern deep learning, yet there is no mathematical description of their benefits and deficiencies as compar…
Greedy bi-criteria approximations for -medians and -means
Daniel Hsu, Matus Telgarsky
This paper investigates the following natural greedy procedure for clustering in the bi-criterion setting: iteratively grow a set of centers, in each round adding the center from a…
Learning Sparse Low-Threshold Linear Classifiers
Sivan Sabato, Shai Shalev-Shwartz, Nathan Srebro +2
We consider the problem of learning a non-negative linear classifier with a -norm of at most , and a fixed threshold, under the hinge-loss. This problem generalizes the probl…
Biased Programmers? Or Biased Data? A Field Experiment in Operationalizing AI Ethics
Bo Cowgill, Fabrizio Dell'Acqua, Samuel Deng +3
Why do biased predictions arise? What interventions can prevent them? We evaluate 8.2 million algorithmic predictions of math performance from 400 AI engineers, each of wh…
Weakly Supervised Attention Networks for Fine-Grained Opinion Mining and Public Health
Giannis Karamanolakis, Daniel Hsu, Luis Gravano
In many review classification applications, a fine-grained analysis of the reviews is desirable, because different segments (e.g., sentences) of a review may focus on different asp…
Modulation of superconductivity by spin canting in a hybrid antiferromagnet/superconductor oxide
Awadhesh Mani, T. Geetha Kumary, Daniel Hsu +2
The proximity effect of a C-type antiferromagnet (C-AFM) with the spin canting at low temperature is investigated in the hybrid Nd0.35Sr0.65MnO3(NSCO)/YBa2Cu3O7(YBCO) oxide system…
Statistical-Computational Trade-offs in Tensor PCA and Related Problems via Communication Complexity
Rishabh Dudeja, Daniel Hsu
Tensor PCA is a stylized statistical inference problem introduced by Montanari and Richard to study the computational difficulty of estimating an unknown parameter from higher-orde…
Parallel Online Learning
Daniel Hsu, Nikos Karampatziakis, John Langford +1
In this work we study parallelization of online learning, a core primitive in machine learning. In a parallel environment all known approaches for parallel online learning lead to…
Bayesian decision-making under misspecified priors with applications to meta-learning
Max Simchowitz, Christopher Tosh, Akshay Krishnamurthy +4
Thompson sampling and other Bayesian sequential decision-making algorithms are among the most popular approaches to tackle explore/exploit trade-offs in (contextual) bandits. The c…
Leveraging Just a Few Keywords for Fine-Grained Aspect Detection Through Weakly Supervised Co-Training
Giannis Karamanolakis, Daniel Hsu, Luis Gravano
User-generated reviews can be decomposed into fine-grained segments (e.g., sentences, clauses), each evaluating a different aspect of the principal entity (e.g., price, quality, ap…
Time-Aware Synthetic Control
Saeyoung Rho, Cyrus Illick, Samhitha Narasipura +3
The synthetic control (SC) framework is widely used for observational causal inference with time-series panel data. SC has been successful in diverse applications, but existing met…
Learning Topic Models and Latent Bayesian Networks Under Expansion Constraints
Animashree Anandkumar, Daniel Hsu, Adel Javanmard +1
Unsupervised estimation of latent variable models is a fundamental problem central to numerous applications of machine learning and statistics. This work presents a principled appr…
Spectral Methods for Learning Multivariate Latent Tree Structure
Animashree Anandkumar, Kamalika Chaudhuri, Daniel Hsu +3
This work considers the problem of learning the structure of multivariate linear tree models, which include a variety of directed tree graphical models with continuous, discrete, a…
Multi-group Learning for Hierarchical Groups
Samuel Deng, Daniel Hsu
The multi-group learning model formalizes the learning scenario in which a single predictor must generalize well on multiple, possibly overlapping subgroups of interest. We extend…
Learning Compositional Functions with Transformers from Easy-to-Hard Data
Zixuan Wang, Eshaan Nichani, Alberto Bietti +4
Transformer-based language models have demonstrated impressive capabilities across a range of complex reasoning tasks. Prior theoretical work exploring the expressive power of tran…
Non-Gaussian information from weak lensing data via deep learning
Arushi Gupta, José Manuel Zorrilla Matilla, Daniel Hsu +1
Weak lensing maps contain information beyond two-point statistics on small scales. Much recent work has tried to extract this information through a range of different observables o…
Correcting the bias in least squares regression with volume-rescaled sampling
MichaÅ DereziÅski, Manfred K. Warmuth, Daniel Hsu
Consider linear regression where the examples are generated by an unknown distribution on . Without any assumptions on the noise, the linear least squares solution for…
Learning mixtures of spherical Gaussians: moment methods and spectral decompositions
Daniel Hsu, Sham M. Kakade
This work provides a computationally efficient and statistically consistent moment-based estimator for mixtures of spherical Gaussians. Under the condition that component means are…
Transformers, parallel computation, and logarithmic depth
Clayton Sanford, Daniel Hsu, Matus Telgarsky
We show that a constant number of self-attention layers can efficiently simulate, and be simulated by, a constant number of communication rounds of Massively Parallel Computation.…
Multi-period Time Series Modeling with Sparsity via Bayesian Variational Inference
Daniel Hsu
In this paper, we use augmented the hierarchical latent variable model to model multi-period time series, where the dynamics of time series are governed by factors or trends in mul…
Intrinsic dimensionality and generalization properties of the -norm inductive bias
Navid Ardeshir, Daniel Hsu, Clayton Sanford
We study the structural and statistical properties of -norm minimizing interpolants of datasets labeled by specific target functions. The -norm is the bas…
Agnostic Active Learning Without Constraints
Alina Beygelzimer, Daniel Hsu, John Langford +1
We present and analyze an agnostic active learning algorithm that works without keeping a version space. This is unlike all previous approaches where a restricted set of candidate…
Greedy Approaches to Symmetric Orthogonal Tensor Decomposition
Cun Mu, Daniel Hsu, Donald Goldfarb
Finding the symmetric and orthogonal decomposition (SOD) of a tensor is a recurring problem in signal processing, machine learning and statistics. In this paper, we review, establi…
Ensuring Fairness Beyond the Training Data
Debmalya Mandal, Samuel Deng, Suman Jana +2
We initiate the study of fair classifiers that are robust to perturbations in the training distribution. Despite recent progress, the literature on fairness has largely ignored the…
A One-Inclusion Graph Approach to Multi-Group Learning
Noah Bergam, Samuel Deng, Daniel Hsu
We prove the tightest-known upper bounds on the sample complexity of multi-group learning. Our algorithm extends the one-inclusion graph prediction strategy using a generalization…
Weighted sampling of outer products
Daniel Hsu
This note gives a simple analysis of the randomized approximation scheme for matrix multiplication of Drineas et al (2006) with a particular sampling distribution over outer produc…
Tracking using explanation-based modeling
Kamalika Chaudhuri, Yoav Freund, Daniel Hsu
We study the tracking problem, namely, estimating the hidden state of an object over time, from unreliable and noisy measurements. The standard framework for the tracking problem i…
Contrastive estimation reveals topic posterior information to linear models
Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu
Contrastive learning is an approach to representation learning that utilizes naturally occurring similar and dissimilar pairs of data points to find useful embeddings of data. In t…
Leveraged volume sampling for linear regression
MichaÅ DereziÅski, Manfred K. Warmuth, Daniel Hsu
Suppose an design matrix in a linear regression problem is given, but the response for each point is hidden unless explicitly requested. The goal is to sample only a s…
A Spectral Algorithm for Latent Dirichlet Allocation
Animashree Anandkumar, Dean P. Foster, Daniel Hsu +2
The problem of topic modeling can be seen as a generalization of the clustering problem, in that it posits that observations are generated due to multiple latent factors (e.g., the…
When are Overcomplete Topic Models Identifiable? Uniqueness of Tensor Tucker Decompositions with Structured Sparsity
Animashree Anandkumar, Daniel Hsu, Majid Janzamin +1
Overcomplete latent representations have been very popular for unsupervised feature learning in recent years. In this paper, we specify which overcomplete models can be identified…
A Tensor Approach to Learning Mixed Membership Community Models
Anima Anandkumar, Rong Ge, Daniel Hsu +1
Community detection is the task of detecting hidden communities from observed interactions. Guaranteed community detection has so far been mostly limited to models with non-overlap…
Two models of double descent for weak features
Mikhail Belkin, Daniel Hsu, Ji Xu
The "double descent" risk curve was proposed to qualitatively describe the out-of-sample prediction accuracy of variably-parameterized machine learning models. This article provide…
Learning Tensor Representations for Meta-Learning
Samuel Deng, Yilin Guo, Daniel Hsu +1
We introduce a tensor-based model of shared representation for meta-learning from a diverse set of tasks. Prior works on learning linear representations for meta-learning assume th…
Consistent Risk Estimation in Moderately High-Dimensional Linear Regression
Ji Xu, Arian Maleki, Kamiar Rahnama Rad +1
Risk estimation is at the core of many learning systems. The importance of this problem has motivated researchers to propose different schemes, such as cross validation, generalize…
Coding sets with asymmetric information
Alexandr Andoni, Javad Ghaderi, Daniel Hsu +2
We study the following one-way asymmetric transmission problem, also a variant of model-based compressed sensing: a resource-limited encoder has to report a small set from a un…
Scalable Nonlinear Learning with Adaptive Polynomial Expansions
Alekh Agarwal, Alina Beygelzimer, Daniel Hsu +2
Can we effectively learn a nonlinear representation in time comparable to linear learning? We describe a new algorithm that explicitly and adaptively expands higher-order interacti…
A New Framework for Query Efficient Active Imitation Learning
Daniel Hsu
We seek to align agent policy with human expert behavior in a reinforcement learning (RL) setting, without any prior knowledge about dynamics, reward function, and unsafe states. T…
A cryptographic approach to black box adversarial machine learning
Kevin Shi, Daniel Hsu, Allison Bishop
We propose a new randomized ensemble technique with a provable security guarantee against black-box transfer attacks. Our proof constructs a new security problem for random binary…
Group conditional validity via multi-group learning
Samuel Deng, Navid Ardeshir, Daniel Hsu
We consider the problem of distribution-free conformal prediction and the criterion of group conditional validity. This criterion is motivated by many practical scenarios including…
Mixing Time Estimation in Reversible Markov Chains from a Single Sample Path
Daniel Hsu, Aryeh Kontorovich, Csaba Szepesvári
This article provides the first procedure for computing a fully data-dependent interval that traps the mixing time of a finite reversible ergodic Markov chain at a…
Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits
Alekh Agarwal, Daniel Hsu, Satyen Kale +3
We present a new algorithm for the contextual bandit learning problem, where the learner repeatedly takes one of actions in response to the observed context, and observes the r…
Random design analysis of ridge regression
Daniel Hsu, Sham M. Kakade, Tong Zhang
This work gives a simultaneous analysis of both the ordinary least squares estimator and the ridge regression estimator in the random design setting under mild assumptions on the c…
Interactive Machine Teaching by Labeling Rules and Instances
Giannis Karamanolakis, Daniel Hsu, Luis Gravano
Weakly supervised learning aims to reduce the cost of labeling data by using expert-designed labeling rules. However, existing methods require experts to design effective rules in…
Seasonality Patterns in 311-Reported Foodborne Illness Cases and Machine Learning-Identified Indications of Foodborne Illnesses from Yelp Reviews, New York City, 2022-2023
Eden Shaveet, Crystal Su, Daniel Hsu +1
Restaurants are critical venues at which to investigate foodborne illness outbreaks due to shared sourcing, preparation, and distribution of foods. Formal channels to report illnes…
Anomaly Detection on Graph Time Series
Daniel Hsu
In this paper, we use variational recurrent neural network to investigate the anomaly detection problem on graph time series. The temporal correlation is modeled by the combination…
Prior Knowledge Makes It Possible: From Sublinear Graph Algorithms to LLM Test-Time Methods
Avrim Blum, Daniel Hsu, Cyrus Rashtchian +1
Test-time augmentation, such as Retrieval-Augmented Generation (RAG) or tool use, critically depends on an interplay between a model's parametric knowledge and externally retrieved…
Investigating the Association Between Text-Based Indications of Foodborne Illness from Yelp Reviews and New York City Health Inspection Outcomes (2023)
Eden Shaveet, Crystal Su, Daniel Hsu +1
Foodborne illnesses are gastrointestinal conditions caused by consuming contaminated food. Restaurants are critical venues to investigate outbreaks because they share sourcing, pre…
Survey on Algorithms for multi-index models
Joan Bruna, Daniel Hsu
We review the literature on algorithms for estimating the index space in a multi-index model. The primary focus is on computationally efficient (polynomial-time) algorithms in Gaus…
Dimension lower bounds for linear approaches to function approximation
Daniel Hsu
This short note presents a linear algebraic approach to proving dimension lower bounds for linear methods that solve function approximation problems. The basic argument has a…