2 citations · 18 across the 31 of their papers we have counts for
37 papers
StochLOB: Heavy-Tailed Score Matching for Robust Limit Order Book Trend Prediction
Arshia Abolghasemi, Seyed Reza Tavakoli, Parsa Naderi +7
Score-based diffusion methods usually perturb data with Brownian Gaussian noise, corresponding to a light-tailed forward stochastic differential equation (SDE). For market time ser…
SCOPD: Sparse-Context On-Policy Self-Distillation for Efficient Vision-Language Models
Ahmadreza Jeddi, Enming Zhang, Jasper Gerigk +12
Reasoning vision-language models (VLMs) process images and videos as long sequences of visual tokens, making inference expensive. Training-free token pruning reduces this cost, but…
Geometry-Adaptive Mechanisms for Private Synthetic Data
Raoof Zare Moayedi, Amir R. Asadi, Mohammad Hossein Yassaee +1
Generating differentially private synthetic data with meaningful Wasserstein utility guarantees is challenging in high dimensions. For datasets of size \(n\) on with $d\g…
On the Generalization and Robustness in Conditional Value-at-Risk
Dinesh Karthik Mulumudi, Piyushi Manupriya, Gholamali Aminian +1
Conditional Value-at-Risk (CVaR) is a widely used risk-sensitive objective for learning under rare but high-impact losses, yet its statistical behavior under heavy-tailed data rema…
-FUM: Federated Unlearning via min--max and -divergence
Radmehr Karimian, Amirhossein Bagheri, Meghdad Kurmanji +2
Federated learning (FL) enables collaborative training while keeping raw data on clients. Deletion requests and the discovery of poisoned data create a need to remove selected cont…
ReDiF: Resource-Efficient Few-Step Diffusion Distillation via Reinforcement Learning
Amirhossein Tighkhorshid, Zahra Dehghanian, Gholamali Aminian +2
Step distillation accelerates diffusion sampling by training a few-step student to imitate a many-step teacher, but distillation itself remains expensive. Typically, this requires…
FraudTransformer: Time-Aware GPT for Transaction Fraud Detection
Gholamali Aminian, Andrew Elliott, Tiger Li +8
Detecting payment fraud in real-world banking streams requires models that can exploit both the order of events and the irregular time gaps between them. We introduce FraudTransfor…
Best-of-N through the Smoothing Lens: KL Divergence and Regret Analysis
Gholamali Aminian, Idan Shenfeld, Amir R. Asadi +2
A simple yet effective method for inference-time alignment of generative models is Best-of- (BoN), where outcomes are sampled from a reference policy, evaluated using a prox…
Log-Sum-Exponential Estimator for Off-Policy Evaluation and Learning
Armin Behnamnia, Gholamali Aminian, Alireza Aghaei +3
Off-policy learning and evaluation leverage logged bandit feedback datasets, which contain context, action, propensity score, and feedback for each data point. These scenarios face…
Semi-pessimistic Reinforcement Learning
Jin Zhu, Xin Zhou, Jiaang Yao +5
Offline reinforcement learning (RL) aims to learn an optimal policy from pre-collected data. However, it faces challenges of distributional shift, where the learned policy may enco…
Generalization Error of -Divergence Stabilized Algorithms via Duality
Francisco Daunas, Iñaki Esnaola, Samir M. Perlaza +1
The solution to empirical risk minimization with -divergence regularization (ERM-DR) is extended to constrained optimization problems, establishing conditions for equivalence…
Private Synthetic Graph Generation and Fused Gromov-Wasserstein Distance
Leoni Carla Wirth, Gholamali Aminian, Gesine Reinert
Networks are popular for representing complex data. In particular, differentially private synthetic networks are much in demand for method and algorithm development. The network ge…
UPL: Uncertainty-aware Pseudo-labeling for Imbalance Transductive Node Classification
Mohammad T. Teimuri, Zahra Dehghanian, Gholamali Aminian +1
Graph-structured datasets often suffer from class imbalance, which complicates node classification tasks. In this work, we address this issue by first providing an upper bound on p…
KL-Regularized RLHF with Multiple Reference Models: Exact Solutions and Sample Complexity
Gholamali Aminian, Amir R. Asadi, Idan Shenfeld +1
Recent methods for aligning large language models (LLMs) with human feedback predominantly rely on a single reference model, which limits diversity, model overfitting, and underuti…
Understanding Transfer Learning via Mean-field Analysis
Gholamali Aminian, Łukasz Szpruch, Samuel N. Cohen
We propose a novel framework for exploring generalization errors of transfer learning through the lens of differential calculus on the space of probability measures. In particular,…
Generalization and Robustness of the Tilted Empirical Risk
Gholamali Aminian, Amir R. Asadi, Tian Li +3
The generalization error (risk) of a supervised statistical learning algorithm quantifies its prediction ability on previously unseen data. Inspired by exponential tilting, \citet{…
An Algorithm for Computing the Capacity of Symmetrized KL Information for Discrete Channels
Haobo Chen, Gholamali Aminian, Yuheng Bu
Symmetrized Kullback-Leibler (KL) information (\(I_{\mathrm{SKL}}\)), which symmetrizes the traditional mutual information by integrating Lautum information, has been shown as a cr…
Robust Semi-supervised Learning via -Divergence and -Rényi Divergence
Gholamali Aminian, Amirhossien Bagheri, Mahyar JafariNodeh +2
This paper investigates a range of empirical risk functions and regularization methods suitable for self-training methods in semi-supervised learning. These approaches draw inspira…
Generalization Error of Graph Neural Networks in the Mean-field Regime
Gholamali Aminian, Yixuan He, Gesine Reinert +2
This work provides a theoretical framework for assessing the generalization error of graph neural networks in the over-parameterized regime, where the number of parameters surpasse…
Mean-field Analysis of Generalization Errors
Gholamali Aminian, Samuel N. Cohen, Łukasz Szpruch
We propose a novel framework for exploring weak and generalization errors of algorithms through the lens of differential calculus on the space of probability measures. Specif…
On the Generalization Error of Meta Learning for the Gibbs Algorithm
Yuheng Bu, Harsha Vardhan Tetali, Gholamali Aminian +2
We analyze the generalization ability of joint-training meta learning algorithms via the Gibbs algorithm. Our exact characterization of the expected meta generalization error for t…
Information-theoretic Characterizations of Generalization Error for the Gibbs Algorithm
Gholamali Aminian, Yuheng Bu, Laura Toni +2
Various approaches have been developed to upper bound the generalization error of a supervised learning algorithm. However, existing bounds are often loose and even vacuous when ev…
How Does Pseudo-Labeling Affect the Generalization Error of the Semi-Supervised Gibbs Algorithm?
Haiyun He, Gholamali Aminian, Yuheng Bu +2
We provide an exact characterization of the expected generalization error (gen-error) for semi-supervised learning (SSL) with pseudo-labeling via the Gibbs algorithm. The gen-error…
Learning Algorithm Generalization Error Bounds via Auxiliary Distributions
Gholamali Aminian, Saeed Masiha, Laura Toni +1
Generalization error bounds are essential for comprehending how well machine learning models work. In this work, we suggest a novel method, i.e., the Auxiliary Distribution Method,…