36 citations · 39 across the 15 of their papers we have counts for
17 papers
TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning
Alliot Nagle, Jakhongir Saydaliev, Dhia Garbaya +3
Large Reasoning Models (LRMs) achieve impressive performance on complex reasoning tasks via Chain-of-Thought (CoT) reasoning, which enables them to generate intermediate thinking t…
Non-Asymptotic Analysis of Efficiency in Conformalized Regression
Yunzhen Yao, Lie He, Michael Gastpar
Conformal prediction provides prediction sets with coverage guarantees. The informativeness of conformal prediction depends on its efficiency, typically quantified by the expected…
The Conditional Regret-Capacity Theorem for Batch Universal Prediction
Marco Bondaschi, Michael Gastpar
We derive a conditional version of the classical regret-capacity theorem. This result can be used in universal prediction to find lower bounds on the minimal batch regret, which is…
What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains
Chanakya Ekbote, Marco Bondaschi, Nived Rajaraman +4
In-context learning (ICL) is a hallmark capability of transformers, through which trained models learn to adapt to new tasks by leveraging information from the input context. Prior…
zip2zip: Inference-Time Adaptive Tokenization via Online Compression
Saibo Geng, Nathan Ranchin, Yunzhen yao +4
Tokenization efficiency plays a critical role in the performance and cost of large language models (LLMs), yet most models rely on static tokenizers optimized on general-purpose co…
From Markov to Laplace: How Mamba In-Context Learns Markov Chains
Marco Bondaschi, Nived Rajaraman, Xiuying Wei +5
While transformer-based language models have driven the AI revolution thus far, their computational complexity has spurred growing interest in viable alternatives, such as structur…
Leveraging Sparsity for Sample-Efficient Preference Learning: A Theoretical Perspective
Yunzhen Yao, Lie He, Michael Gastpar
This paper considers the sample-efficiency of preference learning, which models and predicts human choices based on comparative judgments. The minimax optimal estimation error rate…
Batch Normalization Decomposed
Ido Nachum, Marco Bondaschi, Michael Gastpar +1
\emph{Batch normalization} is a successful building block of neural network architectures. Yet, it is not well understood. A neural network layer with batch normalization comprises…
Which Algorithms Have Tight Generalization Bounds?
Michael Gastpar, Ido Nachum, Jonathan Shafer +1
We study which machine learning algorithms have tight generalization bounds. First, we present conditions that preclude the existence of tight generalization bounds. Specifically,…
Could ChatGPT get an Engineering Degree? Evaluating Higher Education Vulnerability to AI Assistants
Beatriz Borges, Negar Foroutan, Deniz Bayazit +87
AI assistants are being increasingly used by students enrolled in higher education institutions. While these tools provide opportunities for improved teaching and education, they a…
Transformers on Markov Data: Constant Depth Suffices
Nived Rajaraman, Marco Bondaschi, Kannan Ramchandran +2
Attention-based transformers have been remarkably successful at modeling generative processes across various domains and modalities. In this paper, we study the behavior of transfo…
Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models
Alliot Nagle, Adway Girish, Marco Bondaschi +3
We formalize the problem of prompt compression for large language models (LLMs) and present a framework to unify token-level prompt compression methods which create hard prompts fo…
Local to Global: Learning Dynamics and Effect of Initialization for Transformers
Ashok Vardhan Makkuva, Marco Bondaschi, Chanakya Ekbote +4
In recent years, transformer-based models have revolutionized deep learning, particularly in sequence modeling. To better understand this phenomenon, there is a growing interest in…
Batch Universal Prediction
Marco Bondaschi, Michael Gastpar
Large language models (LLMs) have recently gained much popularity due to their surprising ability at generating human-like English sentences. LLMs are essentially predictors, estim…
Attention with Markov: A Framework for Principled Analysis of Transformers via Markov Chains
Ashok Vardhan Makkuva, Marco Bondaschi, Adway Girish +4
Attention-based transformers have achieved tremendous success across a variety of disciplines including natural languages. To deepen our understanding of their sequential modeling…
LASER: Linear Compression in Wireless Distributed Optimization
Ashok Vardhan Makkuva, Marco Bondaschi, Thijs Vogels +3
Data-parallel SGD is the de facto algorithm for distributed optimization, especially for large scale machine learning. Despite its merits, communication bottleneck is one of its pe…
A Johnson--Lindenstrauss Framework for Randomly Initialized CNNs
Ido Nachum, Jan Hązła, Michael Gastpar +1
How does the geometric representation of a dataset change after the application of each randomly initialized layer of a neural network? The celebrated Johnson--Lindenstrauss lemma…