AIConfPaper
← Search

Stratis Ioannidis

16 accepted papers

2025

H-SPLID: HSIC-based Saliency Preserving Latent Information Decomposition

Lukas Miklautz, Chengzhi Shi, Andrii Shkabrii, Theodoros Thirimachos Davarakis, Prudence Lam, Claudia Plant +2
NeurIPS 2025poster

We introduce H-SPLID, a novel algorithm for learning salient feature representations through the explicit decomposition of salient and non-salient features into separate spaces. We show that H-SPLID promotes learning low-dimensional, task-relevant features. We prove that the expected prediction devi…

Cited by 0Source ↗Scholar ↗
2025

Neural Point Processes for Pixel-wise Regression

Chengzhi Shi, Gözde Özcan, Miquel Sirera Perelló, Yuanyuan Li, Nina Iftikhar Shamsi, Stratis Ioannidis
AISTATS 2025poster

We study pixel-wise regression problems with sparsely annotated images. Traditional regression methods based on mean squared error emphasize pixels with labels, leading to distorted predictions in unlabeled areas. To address this limitation, we introduce Neural Point Processes, a novel approach that…

Cited by 0Source ↗Scholar ↗
2024

Efficient Federated Learning against Heterogeneous and Non-stationary Client Unavailability

Ming Xiang, Stratis Ioannidis, Edmund Yeh, Carlee Joe-Wong, Lili Su
NeurIPS 2024poster

Addressing intermittent client availability is critical for the real-world deployment of federated learning algorithms. Most prior work either overlooks the potential non-stationarity in the dynamics of client unavailability or requires substantial memory/computation overhead. We study federated lea…

Cited by 6Source ↗PDF ↗code ↗Scholar ↗
2024

Exploring Token Pruning in Vision State Space Models

Zheng Zhan, Zhenglun Kong, Yifan Gong, Yushu Wu, Zichong Meng, Hangyu Zheng +5
NeurIPS 2024poster

State Space Models (SSMs) have the advantage of keeping linear computational complexity compared to attention modules in transformers, and have been applied to vision tasks as a new type of powerful vision foundation model. Inspired by the observations that the final prediction in vision transformer…

Cited by 6Source ↗PDF ↗Scholar ↗
2024

Online Submodular Maximization via Online Convex Optimization

Tareq Si Salem, Gözde Özcan, Iasonas Nikolaou, Evimaria Terzi, Stratis Ioannidis
AAAI 2024technical

We study monotone submodular maximization under general matroid constraints in the online setting. We prove that online optimization of a large class of submodular functions, namely, threshold potential functions, reduces to online convex optimization (OCO). This is precisely because functions in th…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2023

DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning

Zifeng Wang, Zheng Zhan, Yifan Gong, Yucai Shao, Stratis Ioannidis, Yanzhi Wang +1
ICML 2023poster

Rehearsal-based approaches are a mainstay of continual learning (CL). They mitigate the catastrophic forgetting problem by maintaining a small fixed-size buffer with a subset of data from past tasks. While most rehearsal-based approaches exploit the knowledge from buffered past data, little attentio…

Cited by 12Source ↗PDF ↗Scholar ↗
2023

SmoothHess: ReLU Network Feature Interactions via Stein's Lemma

Max Torop, Aria Masoomi, Davin Hill, Kivanc Kose, Stratis Ioannidis, Jennifer Dy
NeurIPS 2023poster

Several recent methods for interpretability model feature interactions by looking at the Hessian of a neural network. This poses a challenge for ReLU networks, which are piecewise-linear and thus have a zero Hessian almost everywhere. We propose SmoothHess, a method of estimating second-order intera…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗
2022

Differentially Private Regression with Unbounded Covariates

Jason Milionis, Alkis Kalavasis, Dimitris Fotakis, Stratis Ioannidis
AISTATS 2022poster

We provide computationally efficient, differentially private algorithms for the classical regression settings of Least Squares Fitting, Binary Regression and Linear Regression with unbounded covariates. Prior to our work, privacy constraints in such regression settings were studied under strong a pr…

Cited by 16Source ↗PDF ↗Scholar ↗
2022

Explanations of Black-Box Models based on Directional Feature Interactions

Aria Masoomi, Davin Hill, Zhonghui Xu, Craig P Hersh, Edwin K. Silverman, Peter J. Castaldi +2
ICLR 2022spotlight

As machine learning algorithms are deployed ubiquitously to a variety of domains, it is imperative to make these often black-box models transparent. Several recent works explain black-box models by capturing the most influential features for prediction per instance; such explanation methods are uni…

Cited by 33Source ↗PDF ↗code ↗Scholar ↗
2022

SparCL: Sparse Continual Learning on the Edge

Zifeng Wang, Zheng Zhan, Yifan Gong, Geng Yuan, Wei Niu, Tong Jian +4
NeurIPS 2022accept

Existing work in continual learning (CL) focuses on mitigating catastrophic forgetting, i.e., model performance deterioration on past tasks when learning a new task. However, the training efficiency of a CL system is under-investigated, which limits the real-world application of CL systems under res…

Cited by 74Source ↗PDF ↗code ↗Scholar ↗
2021

Deep Spectral Ranking

Ilkay Yildiz, Jennifer Dy, Deniz Erdogmus, Susan Ostmo, J. Peter Campbell, Michael F. Chiang +1
AISTATS 2021poster

Learning from ranking observations arises in many domains, and siamese deep neural networks have shown excellent inference performance in this setting. However, SGD does not scale well, as an epoch grows exponentially with the ranking observation size. We show that a spectral algorithm can be combin…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2021

Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness

Zifeng Wang, Tong Jian, Aria Masoomi, Stratis Ioannidis, Jennifer Dy
NeurIPS 2021poster

We investigate the HSIC (Hilbert-Schmidt independence criterion) bottleneck as a regularizer for learning an adversarially robust deep neural network classifier. In addition to the usual cross-entropy loss, we add regularization terms for every intermediate layer to ensure that the latent representa…

Cited by 31Source ↗PDF ↗code ↗Scholar ↗
2020

Fast and Accurate Ranking Regression

Ilkay Yildiz, Jennifer Dy, Deniz Erdogmus, Jayashree Kalpathy-Cramer, Susan Ostmo, J. Peter Campbell +2
AISTATS 2020poster

We consider a ranking regression problem in which we use a dataset of ranked choices to learn Plackett-Luce scores as functions of sample features. We solve the maximum likelihood estimation problem by using the Alternating Directions Method of Multipliers (ADMM), effectively separating the learning…

Cited by 14Source ↗PDF ↗code ↗Scholar ↗
2018

Iterative Spectral Method for Alternative Clustering

Chieh Wu, Stratis Ioannidis, Mario Sznaier, Xiangyu Li, David Kaeli, Jennifer Dy
AISTATS 2018poster

Given a dataset and an existing clustering as input, alternative clustering aims to find an alternative partition. One of the state-of-the-art approaches is Kernel Dimension Alternative Clustering (KDAC). We propose a novel Iterative Spectral Method (ISM) that greatly improves the scalability of…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗