2 citations · 3 across the 17 of their papers we have counts for
22 papers
Explore Broadly, Reason Sharply: Push Small Models toward the Frontier via Sampling
Panagiotis Theodoropoulos, Nan Jiang, Xintong Duan +4
Power-sharpened sampling is an inference-time alternative to reinforcement-learning (RL) post-training for enhancing reasoning in large language models (LLMs). High-probability seq…
Scaling the Queue: Reinforcement Learning for Equitable Call Classification Capacity in NYC Municipal Complaint Systems
Irene Aldridge, Ellie Bae, Siddhesh Darak +25
Municipal 311 call centers and complaint intake systems face a structural mismatch between incoming volume and classification capacity. The staff and heuristics available to triage…
Score-based Metropolis-Hastings for Fractional Langevin Algorithms
Ahmed Aloui, Junyi Liao, Ali Hasan +2
Sampling from heavy-tailed and multimodal distributions is challenging when neither the target density nor the proposal density can be evaluated, as in -stable Lévy-driven fract…
How Does the Pretraining Distribution Shape In-Context Learning? A Fundamental Trade-Off
Waïss Azizian, Ali Hasan
The factors driving the performance of in-context learning (ICL) in large language models (LLMs) remain poorly understood despite ICL's surprising effectiveness, enabling models to…
Automatic Question & Answer Generation Using Generative Large Language Model (LLM)
Md. Alvee Ehsan, A. S. M Mehedi Hasan, Kefaya Benta Shahnoor +1
In the realm of education, student evaluation holds equal significance to imparting knowledge. To be evaluated, students usually need to go through text-based academic assessment m…
Conditional Average Treatment Effect Estimation Under Hidden Confounders
Ahmed Aloui, Juncheng Dong, Ali Hasan +1
One of the major challenges in estimating conditional potential outcomes and conditional average treatment effects (CATE) is the presence of hidden confounders. Since testing for h…
Elliptic Loss Regularization
Ali Hasan, Haoming Yang, Yuting Ng +1
Regularizing neural networks is important for anticipating model behavior in regions of the data space that are not well represented. In this work, we propose a regularization tech…
Parabolic Continual Learning
Haoming Yang, Ali Hasan, Vahid Tarokh
Regularizing continual learning techniques is important for anticipating algorithmic behavior under new realizations of data. We introduce a new approach to continual learning by i…
Score-Based Metropolis-Hastings Algorithms
Ahmed Aloui, Ali Hasan, Juncheng Dong +2
In this paper, we introduce a new approach for integrating score-based models with the Metropolis-Hastings algorithm. While traditional score-based diffusion models excel in accura…
Distributionally Robust Optimization as a Scalable Framework to Characterize Extreme Value Distributions
Patrick Kuiper, Ali Hasan, Wenhao Yang +4
The goal of this paper is to develop distributionally robust optimization (DRO) estimators, specifically for multidimensional Extreme Value Theory (EVT) statistics. EVT supports us…
Base Models for Parabolic Partial Differential Equations
Xingzi Xu, Ali Hasan, Jie Ding +1
Parabolic partial differential equations (PDEs) appear in many disciplines to model the evolution of various mathematical objects, such as probability flows, value functions in con…
Neural McKean-Vlasov Processes: Distributional Dependence in Diffusion Processes
Haoming Yang, Ali Hasan, Yuting Ng +1
McKean-Vlasov stochastic differential equations (MV-SDEs) provide a mathematical description of the behavior of an infinite number of interacting particles by imposing a dependence…
Perceiver-based CDF Modeling for Time Series Forecasting
Cat P. Le, Chris Cannella, Ali Hasan +2
Transformers have demonstrated remarkable efficacy in forecasting time series data. However, their extensive dependence on self-attention mechanisms demands significant computation…
Treatment Effects in Extreme Regimes
Ahmed Aloui, Ali Hasan, Yuting Ng +2
Understanding treatment effects in extreme regimes is important for characterizing risks associated with different interventions. This is hindered by the unavailability of counterf…
Inference and Sampling of Point Processes from Diffusion Excursions
Ali Hasan, Yu Chen, Yuting Ng +3
Point processes often have a natural interpretation with respect to a continuous process. We propose a point process construction that describes arrival time observations in terms…
Inference and Sampling for Archimax Copulas
Yuting Ng, Ali Hasan, Vahid Tarokh
Understanding multivariate dependencies in both the bulk and the tails of a distribution is an important problem for many applications, such as ensuring algorithms are robust to ob…
Characteristic Neural Ordinary Differential Equations
Xingzi Xu, Ali Hasan, Khalil Elkhalil +2
We propose Characteristic-Neural Ordinary Differential Equations (C-NODEs), a framework for extending Neural Ordinary Differential Equations (NODEs) beyond ODEs. While NODEs model…
Generative Archimedean Copulas
Yuting Ng, Ali Hasan, Khalil Elkhalil +1
We propose a new generative modeling technique for learning multidimensional cumulative distribution functions (CDFs) in the form of copulas. Specifically, we consider certain clas…
Modeling Extremes with d-max-decreasing Neural Networks
Ali Hasan, Khalil Elkhalil, Yuting Ng +4
We propose a novel neural network architecture that enables non-parametric calibration and generation of multivariate extreme value distributions (MEVs). MEVs arise from Extreme Va…
Fisher Auto-Encoders
Khalil Elkhalil, Ali Hasan, Jie Ding +2
It has been conjectured that the Fisher divergence is more robust to model uncertainty than the conventional Kullback-Leibler (KL) divergence. This motivates the design of a new cl…
Identifying Latent Stochastic Differential Equations
Ali Hasan, João M. Pereira, Sina Farsiu +1
We present a method for learning latent stochastic differential equations (SDEs) from high-dimensional time series data. Given a high-dimensional time series generated from a lower…
Learning Partial Differential Equations from Data Using Neural Networks
Ali Hasan, João M. Pereira, Robert Ravier +2
We develop a framework for estimating unknown partial differential equations from noisy data, using a deep learning approach. Given noisy samples of a solution to an unknown PDE, o…