arXiv subjects

Yitan Wang

Publications and source records attributed to Yitan Wang.

9 recordsLinked to original sources

arXiv2026

On the Impossibility of Specification Testing of Interference Models Based on Exposure Mappings

Researchers use interference models based on exposure mappings to facilitate estimation of causal effects in randomized experiments with interference. To test the veracity of such models, researchers can use specification tests that aim to detect departures from the stipulated model. However, existing tests suffer from poor power and are often unable to detect important model violations. The main result in this paper is to show that the specification testing problem for exposure mapping models is inherently difficult, and the poor power of existing tests is inescapable. In particular, the worst-case Type I and Type II error rates must sum to one for any specification test of such models, ruling out the existence of a uniformly consistent test. This is the worst-case overall error rate achieved by a naive test that discards all data and arbitrarily rejects the null at random; the testing problem is in this sense impossible. This negative result holds true for all exposure mappings, all sample sizes, for uniformly bounded outcomes, and for alternatives that are maximally separated from the null. While some tests can detect some type of departures from the null model, there will always be relevant departures from the null that are undetectable. Informative specification tests must therefore restrict the alternative model against which they seek to attain power for, beyond the restrictions imposed by the exposure mappings alone. We illustrate this by providing a uniformly consistent test for differentiating no-interference from a network-linear-in-means model.

math.ST↗

arXiv2023

Toward Highly Efficient and Private Submodular Maximization via Matrix-Based Acceleration

Submodular function maximization is a critical building block for diverse tasks, such as document summarization, sensor placement, and image segmentation. Yet its practical utility is often limit by the $O(knd^2)$ computational bottleneck. In this paper, we propose an integrated framework that addresses efficiency and privacy simultaneously. First, we introduce a novel matrix-based computation paradigm that accelerates function evaluations. Second, we develop approximate data structures that further streamline the optimization process, achieving a theoretical complexity of $O(\epsilon^{-2}(nd+kn+kd^2)\log(k/\delta))$. Third, we integrate ($\epsilon, \delta$)-DP guaranties to address the privacy concerns inherent in sensitive optimization tasks.

cs.LG↗

arXiv2023

A Unified Framework of Policy Learning for Contextual Bandit with Confounding Bias and Missing Observations

We study the offline contextual bandit problem, where we aim to acquire an optimal policy using observational data. However, this data usually contains two deficiencies: (i) some variables that confound actions are not observed, and (ii) missing observations exist in the collected data. Unobserved confounders lead to a confounding bias and missing observations cause bias and inefficiency problems. To overcome these challenges and learn the optimal policy from the observed dataset, we present a new algorithm called Causal-Adjusted Pessimistic (CAP) policy learning, which forms the reward function as the solution of an integral equation system, builds a confidence set, and greedily takes action with pessimism. With mild assumptions on the data, we develop an upper bound to the suboptimality of CAP for the offline contextual bandit problem.

cs.LG↗

arXiv2022

A General Design-Based Framework and Estimator for Randomized Experiments

We describe a design-based framework for drawing causal inference in general randomized experiments. Causal effects are defined as linear functionals evaluated at unit-level potential outcome functions. Assumptions about the potential outcome functions are encoded as function spaces. This makes the framework expressive, allowing experimenters to formulate and investigate a wide range of causal questions, including about interference, that previously could not be investigated with design-based methods. We describe a class of estimators for estimands defined using the framework and investigate their properties. We provide necessary and sufficient conditions for unbiasedness and consistency. We also describe a class of conservative variance estimators, which facilitate the construction of confidence intervals. Finally, we provide several examples of empirical settings that previously could not be examined with design-based methods to illustrate the use of our approach in practice.

stat.ME↗

arXiv2022

A Nearly Optimal Size Coreset Algorithm with Nearly Linear Time

A coreset is a point set containing information about geometric properties of a larger point set. A series of previous works show that in many machine learning problems, especially in clustering problems, coreset could be very useful to build efficient algorithms. Two main measures of an coreset construction algorithm's performance are the running time of the algorithm and the size of the coreset output by the algorithm. In this paper we study the construction of coresets for the $(k,z)$-clustering problem, which is a generalization of $k$-means and $k$-median problem. By properly designing a sketching-based distance estimation data structure, we propose faster algorithms that construct coresets with matching size of the state-of-the-art results.

cs.DS↗

arXiv2022

Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerability

Sketching is one of the most fundamental tools in large-scale machine learning. It enables runtime and memory saving via randomly compressing the original large problem into lower dimensions. In this paper, we propose a novel sketching scheme for the first order method in large-scale distributed learning setting, such that the communication costs between distributed agents are saved while the convergence of the algorithms is still guaranteed. Given gradient information in a high dimension $d$, the agent passes the compressed information processed by a sketching matrix $R\in \mathbb{R}^{s\times d}$ with $s\ll d$, and the receiver de-compressed via the de-sketching matrix $R^\top$ to ``recover'' the information in original dimension. Using such a framework, we develop algorithms for federated learning with lower communication costs. However, such random sketching does not protect the privacy of local data directly. We show that the gradient leakage problem still exists after applying the sketching technique by presenting a specific gradient attack method. As a remedy, we prove rigorously that the algorithm will be differentially private by adding additional random noises in gradient information, which results in a both communication-efficient and differentially private first order approach for federated learning tasks. Our sketching scheme can be further generalized to other learning settings and might be of independent interest itself.

cs.LG↗

arXiv2022

A Sublinear Adversarial Training Algorithm

Adversarial training is a widely used strategy for making neural networks resistant to adversarial perturbations. For a neural network of width $m$, $n$ input training data in $d$ dimension, it takes $\Omega(mnd)$ time cost per training iteration for the forward and backward computation. In this paper we analyze the convergence guarantee of adversarial training procedure on a two-layer neural network with shifted ReLU activation, and shows that only $o(m)$ neurons will be activated for each input data per iteration. Furthermore, we develop an algorithm for adversarial training with time cost $o(m n d)$ per iteration by applying half-space reporting data structure.

cs.LG↗

arXiv2020

Succinct Explanations With Cascading Decision Trees

The decision tree is one of the most popular and classical machine learning models from the 1980s. However, in many practical applications, decision trees tend to generate decision paths with excessive depth. Long decision paths often cause overfitting problems, and make models difficult to interpret. With longer decision paths, inference is also more likely to fail when the data contain missing values. In this work, we propose a new tree model called Cascading Decision Trees to alleviate this problem. The key insight of Cascading Decision Trees is to separate the decision path and the explanation path. Our experiments show that on average, Cascading Decision Trees generate 63.38% shorter explanation paths, avoiding overfitting and thus achieve higher test accuracy. We also empirically demonstrate that Cascading Decision Trees have advantages in the robustness against missing values.

cs.LG↗

arXiv2018

Interpolatron: Interpolation or Extrapolation Schemes to Accelerate Optimization for Deep Neural Networks

In this paper we explore acceleration techniques for large scale nonconvex optimization problems with special focuses on deep neural networks. The extrapolation scheme is a classical approach for accelerating stochastic gradient descent for convex optimization, but it does not work well for nonconvex optimization typically. Alternatively, we propose an interpolation scheme to accelerate nonconvex optimization and call the method Interpolatron. We explain motivation behind Interpolatron and conduct a thorough empirical analysis. Empirical results on DNNs of great depths (e.g., 98-layer ResNet and 200-layer ResNet) on CIFAR-10 and ImageNet show that Interpolatron can converge much faster than the state-of-the-art methods such as the SGD with momentum and Adam. Furthermore, Anderson's acceleration, in which mixing coefficients are computed by least-squares estimation, can also be used to improve the performance. Both Interpolatron and Anderson's acceleration are easy to implement and tune. We also show that Interpolatron has linear convergence rate under certain regularity assumptions.

stat.ML↗