28 accepted papers
We study instrumental variable regression (IVaR) under differential privacy constraints. Classical IVaR methods (like two-stage least squares regression) rely on solving moment equations that directly use sensitive covariates and instruments, creating significant risks of privacy leakage and posing…
Offline Reinforcement Learning from Human Feedback (RLHF) pipelines such as Direct Preference Optimization (DPO) train on a pre-collected preference dataset, which makes them vulnerable to preference poisoning attack. We study label flip attacks against log-linear DPO. We first illustrate that flipp…
Reinforcement learning usually assumes a given or sometimes even fixed environment in which an agent seeks an optimal policy to maximize its long-term discounted reward. In contrast, we consider agents that are not limited to passive adaptations: they instead have model-changing actions that activel…
Discrete state space diffusion models have shown significant advantages in applications involving discrete data, such as text and image generation. It has also been observed that their performance is highly sensitive to the choice of rate matrices, particularly between uniform and absorbing rate mat…
Discrete diffusion models have recently gained significant prominence in applications involving natural language and graph data. A key factor influencing their effectiveness is the efficiency of discretized samplers. Among these, $\tau$-leaping samplers have become particularly popular due to their…
We explore the capability of transformers to address endogeneity in in-context linear regression. Our main finding is that transformers inherently possess a mechanism to handle endogeneity effectively using instrumental variables (IV). First, we demonstrate that the transformer architecture can emul…
Privacy protection of users' entire contribution of samples is important in distributed systems. The most effective approach is the two-stage scheme, which finds a small interval first and then gets a refined estimate by clipping samples into the interval. However, the clipping operation induces bia…
Exploration is a crucial phase in reinforcement learning (RL). The reward-free RL paradigm, as explored by (Jin et al., 2020), offers an efficient method to design exploration algorithms for risk-neutral RL across various reward functions with a single exploration phase. However, as RL applications…
This paper delves into the subject of designing a tree network, enabling the application of Distributed Dual Coordinate Ascent on a general tree network (DDCA-Tree) introduced in [1] – [3] for distributed Machine Learning (ML) process. We assume that a network is characterized by communication delay…
Fairness and robustness are critical elements of trustworthy machine learning systems that need to be addressed. Using a minimax framework, in this paper, we aim to design an adversarially robust fair regression model that achieves optimal performance in the presence of an attacker who is able to pe…
Due to the broad range of applications of multi-agent reinforcement learning (MARL), understanding the effects of adversarial attacks against MARL model is essential for the safe applications of this model. Motivated by this, we investigate the impact of adversarial attacks on MARL. In the considere…
In this paper, we develop a framework to achieve a desirable trade-off between fairness, inference accuracy and privacy protection in the inference as service scenario. Instead of sending raw data to the cloud, we conduct a random mapping of the data, which will increase privacy protection and mitig…
The Wasserstein distance has become increasingly important in machine learning and deep learning. Despite its popularity, the Wasserstein distance is hard to approximate because of the curse of dimensionality. A recently proposed approach to alleviate the curse of dimensionality is to project the sa…
In this paper, we propose an adaptive kNN method for classification, in which different k are selected for different test samples. Our selection rule is easy to implement since it is completely adaptive and does not require any knowledge of the underlying distribution. The convergence rate of the ri…
In this paper, we investigate the adversarial robustness of principal component analysis (PCA) algorithms. In the considered setup, there is a powerful adversary who can add a carefully designed data point to the original data matrix. The goal of the adversary is to maximize the distance between the…
In this paper, we propose a general framework to provide a desirable trade-off between inference accuracy and privacy protection in the inference as service scenario. Instead of sending data directly to the server, the user will preprocess the data through a privacy-preserving mapping, which will in…
Collecting and aggregating information from several probability measures or histograms is a fundamental task in machine learning. One of the popular solution methods for this task is to compute the barycenter of the probability measures under the Wasserstein metric. However, approximating the Wasser…
Due to the broad range of applications of reinforcement learning (RL), understanding the effects of adversarial attacks against RL model is essential for the safe applications of this model. Prior theoretical works on adversarial attacks against RL mainly focus on either reward poisoning attacks or…
As stochastic multi-armed bandit model has many important applications, understanding the impact of adversarial attacks on this model is essential for the safe applications of this model. In this paper, we propose a new class of attack named action-manipulation attack, where an adversary can change…
With explosion of data size and limited storage space at a single location, data are often distributed at different locations. We thus face the challenge of performing large-scale machine learning from these distributed data through communication networks. In this paper, we generalize the distribute…
In this paper, we investigate the adversarial robustness of subspace learning problems. Different from the scenario addressed by classic robust algorithms that assume fractions of data are corrupted, we consider a more powerful adversary who can observe the whole data and modify all of them. The goa…
The problem of quickly detecting the occurrence of an unusual event that happens on one of multiple independent data streams is considered. In the considered problem, all data streams at the initial are under normal state and are generated by probability distribution P <sub xmlns:mml="http://www.w3.…
Due to the grow of modern dataset size and the desire to harness computing power of multiple machines, there is a recent surge of interest in the design of distributed machine learning algorithms. However, distributed algorithms are sensitive to Byzantine attackers who can send falsified data to pre…
In this paper, the problem of identifying correlated components in a high-dimensional Gaussian vector is considered. In the setup considered, instead of having to take a full-vector observation at each time index, the observer is allowed to observe any subset or full set of components in the vector,…
We consider problems where one wishes to represent a parameter associated with a signal source - subject to a certain rate and distortion - based on the observation of a number of realizations of the source signal. By reducing these indirect vector quantization problems to a standard vector quantiza…
In this paper, Bayesian quickest change-point detection problem with incomplete post-change information is considered. In particular, the observer knows that the post-change distribution belongs to a parametric distribution family, but he does not know the true value of the post-change parameter. Tw…
In this paper, we consider the problem of quickly detecting an abrupt change of linear coefficients in linear regression models. In particular, the observer sequentially observes a sequence of observations {(xn, yn)}∞n=1, which is assumed to obey a linear regression model at each time slot n. Some o…
Characterizing the phase transitions of convex optimizations in recovering structured signals or data is of central importance in compressed sensing, machine learning and statistics. The phase transitions of many convex optimization signal recovery methods such as ℓ <sub xmlns:mml="http://www.w3.org…