Institution profile

Hebrew University of Jerusalem

Academic institutioneurope · il
Official website
Research library410linked papers
Opportunities0open roles
Selected work

Representative Papers

Unifying Formal Explanations: A Complexity-Theoretic Perspective

Feb 20, 2026

This work establishes a unified theoretical framework for analyzing the computational complexity of sufficient and contrastive explanations in machine learning models. It introduces a general probabilistic value function whose minimization subsumes both explanation types, enabling rigorous analysis through combinatorial optimization and computational complexity theory. The key contribution lies in demonstrating, for the first time, that under global explanation settings, this value function exhibits monotonicity, submodularity, or supermodularity—properties that guarantee efficient polynomial-time computability for a broad class of explanations. In stark contrast, even highly simplified variants become NP-hard in local explanation settings. These results provide a unified theoretical foundation and clear computational feasibility criteria for explainability across diverse model classes, including neural networks and decision trees.

2 citationsRead paper

Will it Merge? On The Causes of Model Mergeability

Jan 10, 2026arXiv.org

Model merging often suffers from unpredictable performance, limiting its practical utility. This work introduces the first quantifiable definition of model mergeability and systematically investigates the key factors influencing merging effectiveness, identifying the base model’s prior knowledge about the fine-tuning data as the decisive factor. Building on this insight, the authors propose a weighted parameter fusion strategy that effectively preserves weak yet relevant knowledge embedded in the base model. Experimental results demonstrate that the proposed method significantly enhances merging performance in multi-task settings, thereby validating the critical role of the base model’s knowledge level in determining the success of model merging.

2 citationsRead paper

High-Rate Quantized Matrix Multiplication: Theory and Practice

Jan 23, 2026

This work addresses the trade-off between accuracy and efficiency in high-rate quantized matrix multiplication for large language models. By leveraging information-theoretic rate-distortion analysis, the authors derive fundamental limits for both joint weight-and-activation quantization and weight-only quantization. They propose WaterSIC, a scheme that dynamically allocates quantization bits based on the water-filling principle, achieving basis-independent near-optimal performance using only scalar integer quantizers. Theoretically, WaterSIC operates within just 0.25 bit per entry of the information-theoretic rate-distortion limit under high-rate conditions. Experiments demonstrate that GPTQ combined with random rotation on Llama-3-8B achieves performance within approximately 0.1 bit of WaterSIC, closely approaching the theoretical optimum.

1 citationsRead paper
Recent publications

Latest Papers