Hamed Hassani

• Behrad Moniri, Seyed Hamed Hassani, Edgar Dobriban, Evaluating the Performance of Large Language Models via Debates.
• Patrick Chao, Edgar Dobriban, Seyed Hamed Hassani, Watermarking Language Models with Error Correcting Codes.
• Xinmeng Huang, Shuo Li, Edgar Dobriban, Osbert Bastani, Seyed Hamed Hassani, Dongsheng Ding, One-Shot Safety Alignment for Large Language Models via Optimal Dualization.
• Xinmeng Huang, Shuo Li, Mengxin Yu, Matteo Sesia, Seyed Hamed Hassani, Insup Lee, Osbert Bastani, Edgar Dobriban, Uncertainty in Language Models: Assessment through Rank-Calibration.
• Patrick Chao, Edoardo Debenedetti, Alexander Robey, Maksym Andriushchenko, Francesco Croce, Vikash Sehwag, Edgar Dobriban, Nicolas Flammarion, George J. Pappas, Florian Tramer, Seyed Hamed Hassani, Eric Wong, JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models.
• Patrick Chao, Alexander Robey, Edgar Dobriban, Seyed Hamed Hassani, George J. Pappas, Eric Wong, Jailbreaking Black Box Large Language Models in Twenty Queries. Related
  Links
• Behrad Moniri, Donghwan Lee, Seyed Hamed Hassani, Edgar Dobriban, A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks. Related
  Links
• Xinmeng Huang, Kan Xu, Donghwan Lee, Seyed Hamed Hassani, Hamsa Bastani, Edgar Dobriban Optimal Heterogeneous Collaborative Linear Regression and Contextual Bandits.
• Donghwan Lee, Behrad Moniri, Xinmeng Huang, Seyed Hamed Hassani, Edgar Dobriban (Work In Progress), Demystifying Disagreement-on-the-Line in High Dimensions. Related
  Links
• Xinmeng Huang, Donghwan Lee, Edgar Dobriban, Seyed Hamed Hassani, Collaborative Learning of Distributions under Heterogeneity and Communication Constraints.

Current Courses

• ESE3060 - Deep Learning: A Hands-on Introduction

  This course will serve as an introductory and hands-on dive into the area of deep learning. The main goal is to to educate the students on (i) the commonly-used neural network architectures and proficiency in training them, (ii) Some of the main problems that deep learning systems have successfully addressed (formulation, architecture, data sets, etc). There will be no theory in this course. After finishing this course, the students should be very comfortable with pytorch programming as well as training deep learning models.

  ESE3060001 ( Syllabus )

• ESE4020 - Statistics For Data Science

  The course covers the methodological foundations of data science, emphasizing basic concepts in statistics and learning theory, but also modern methodologies. Learning of distributions and their parameters. Testing of multiple hypotheses. Linear and nonlinear regression and prediction. Classification. Uncertainty quantification. Model validation. Clustering. Dimensionality reduction. Probably approximately correct (PAC) learning. Such theoretical concepts are further complemented by exempla r applications, case studies (datasets), and programming exercises (in Python) drawn from electrical engineering, computer science, the life sciences, finance, and social networks.

  ESE4020401

  ESE4020402

• ESE5420 - Statistics For Data Science

  The course covers the methodological foundations of data science, emphasizing basic concepts in statistics and learning theory, but also modern methodologies. Learning of distributions and their parameters. Testing of multiple hypotheses. Linear and nonlinear regression and prediction. Classification. Uncertainty quantification. Model validation. Clustering. Dimensionality reduction. Probably approximately correct (PAC) learning. Such theoretical concepts are further complemented by exempla r applications, case studies (datasets), and programming exercises (in Python) drawn from electrical engineering, computer science, the life sciences, finance, and social networks.

  ESE5420401

  ESE5420402

  ESE5420501

• ESE9990 - Thesis/dissertation Research

  For students working on an advanced research program leading to the completion of master's thesis.

  ESE9990006

Past Courses

• AMCS5999 - Independent Study

  Independent Study allows students to pursue academic interests not available in regularly offered courses. Students must consult with their academic advisor to formulate a project directly related to the student’s research interests. All independent study courses are subject to the approval of the AMCS Graduate Group Chair.

• AMCS9999 - Ind Study & Research

  Study under the direction of a faculty member.

• CIS5990 - Master's Indep Study

  For master's students studying a specific advanced subject area in computer and information science. Involves coursework and class presentations. A CIS 5990 course unit will invariably include formally gradable work comparable to that in a CIS 500-level course. Students should discuss with the faculty supervisor the scope of the Independent Study, expectations, work involved, etc.

• ESE0099 - Independent Study

  An opportunity for the student to become closely associated with a professor in (1) a research effort to develop research skills and technique and/or (2) to develop a program of independent in-depth study in a subject area in which the professor and student have a common interest. The challenge of the task undertaken must be consistent with the student's academic level. To register for this course, the student and professor jointly submit a detailed proposal to the undergraduate curriculum chairman no later than the end of the first week of the term.

• ESE3050 - Foundations of Data Sci

  Introduction to a broad range of tools to analyze large volumes of data in order to transform them into actionable decisions. Using case studies and hands-on exercises, the student will have the opportunity to practice and increase their data analysis skills.

• ESE3060 - Deep Learning: A Hands-on Intr

  This course will serve as an introductory and hands-on dive into the area of deep learning. The main goal is to to educate the students on (i) the commonly-used neural network architectures and proficiency in training them, (ii) Some of the main problems that deep learning systems have successfully addressed (formulation, architecture, data sets, etc). There will be no theory in this course. After finishing this course, the students should be very comfortable with pytorch programming as well as training deep learning models.

• ESE4020 - Stat For Data Science

  The course covers the methodological foundations of data science, emphasizing basic concepts in statistics and learning theory, but also modern methodologies. Learning of distributions and their parameters. Testing of multiple hypotheses. Linear and nonlinear regression and prediction. Classification. Uncertainty quantification. Model validation. Clustering. Dimensionality reduction. Probably approximately correct (PAC) learning. Such theoretical concepts are further complemented by exempla r applications, case studies (datasets), and programming exercises (in Python) drawn from electrical engineering, computer science, the life sciences, finance, and social networks.

• ESE5420 - Stat For Data Science

  The course covers the methodological foundations of data science, emphasizing basic concepts in statistics and learning theory, but also modern methodologies. Learning of distributions and their parameters. Testing of multiple hypotheses. Linear and nonlinear regression and prediction. Classification. Uncertainty quantification. Model validation. Clustering. Dimensionality reduction. Probably approximately correct (PAC) learning. Such theoretical concepts are further complemented by exempla r applications, case studies (datasets), and programming exercises (in Python) drawn from electrical engineering, computer science, the life sciences, finance, and social networks.

• ESE5450 - Data Mining

  Many scientific and commercial applications require us to obtain insights from massive, high-dimensional data sets. In this graduate-level course, students will learn to apply, analyze and evaluate principled, state-of-the-art technique s from statistics, algorithms and discrete and convex optimization for learning from such large data sets. The course both covers theoretical foundations and practical applications.

• ESE5970 - Master's Thesis Research

  For students working on an advanced research leading to the completion of a Master's thesis.

• ESE5990 - Master's Indep Study

• ESE6050 - Mdrn Convex Optimization

  This course concentrates on recognizing and solving convex optimization problems that arise in engineering. Topics include: convex sets, functions, and optimization problems. Basis of convex analysis. Linear, quadratic, geometric, and semidefinite programming. Optimality conditions, duality theory, theorems of alternative, and applications. Interior-point methods, ellipsoid algorithm and barrier methods, self-concordance. Applications to signal processing, control, digital and analog circuit design, computation geometry, statistics, and mechanical engineering. Knowledge of linear algebra and willingness to do programming. Exposure to numerical computing, optimization, and application fields is helpful but not required.

• ESE6800 - Special Topcs in Ese

  Advanced and specialized topics in both theory and application areas. Students should check Graduate Group office for offerings during each registration period.

• ESE9990 - Master's Thesis

  For students working on an advanced research program leading to the completion of master's thesis.

Knowledge @ Wharton

• Overwhelmed by Too Many Choices When Shopping? Wharton Retail Expert Weighs In, Knowledge @ Wharton - 12/19/2024
• Michael Lee, Oatly North America’s EVP & Executive Creative Director, Knowledge @ Wharton - 12/19/2024
• Why Anchor Institutions Are Vital to Local Economies, Knowledge @ Wharton - 12/17/2024
• Is the American Dream of Homeownership Still Within Reach?, Knowledge @ Wharton - 12/17/2024
• Even Under Trump, AI Governance Is Here to Stay, Knowledge @ Wharton - 12/17/2024
• 2024 Ripple Rewind (Part 2), Knowledge @ Wharton - 12/17/2024
• What Are the Best Countries of 2024?, Knowledge @ Wharton - 12/16/2024
• Your Pride Could Affect Your Workplace Reputation, Knowledge @ Wharton - 12/12/2024
• Samantha Baker, VP of Commerce at theSkimm, Knowledge @ Wharton - 12/12/2024
• NFL Stats & Analysis with Ben Solak, Knowledge @ Wharton - 12/11/2024