no code implementations • 16 Apr 2024 • Hantian Ding, Zijian Wang, Giovanni Paolini, Varun Kumar, Anoop Deoras, Dan Roth, Stefano Soatto
In large language model training, input documents are typically concatenated together and then split into sequences of equal length to avoid padding tokens.
no code implementations • 22 May 2023 • Karthikeyan K, Yogarshi Vyas, Jie Ma, Giovanni Paolini, Neha Anna John, Shuai Wang, Yassine Benajiba, Vittorio Castelli, Dan Roth, Miguel Ballesteros
We experiment with 6 diverse datasets and show that PLM consistently performs better than most other approaches (0. 5 - 2. 5 F1), including in novel settings for taxonomy expansion not considered in prior work.
no code implementations • 19 May 2023 • Robert Vacareanu, Siddharth Varia, Kishaloy Halder, Shuai Wang, Giovanni Paolini, Neha Anna John, Miguel Ballesteros, Smaranda Muresan
We explore how weak supervision on abundant unlabeled data can be leveraged to improve few-shot performance in aspect-based sentiment analysis (ABSA) tasks.
no code implementations • 15 Feb 2023 • Benjamin Bowman, Alessandro Achille, Luca Zancato, Matthew Trager, Pramuditha Perera, Giovanni Paolini, Stefano Soatto
During inference, models can be assembled based on arbitrary selections of data sources, which we call "\`a-la-carte learning".
no code implementations • CVPR 2023 • Benjamin Bowman, Alessandro Achille, Luca Zancato, Matthew Trager, Pramuditha Perera, Giovanni Paolini, Stefano Soatto
During inference, models can be assembled based on arbitrary selections of data sources, which we call a-la-carte learning.
no code implementations • ICLR 2022 • Yonatan Dukler, Alessandro Achille, Giovanni Paolini, Avinash Ravichandran, Marzia Polito, Stefano Soatto
A learning task is a function from a training set to the validation error, which can be represented by a trained deep neural network (DNN).
no code implementations • 29 Sep 2021 • Luca Zancato, Alessandro Achille, Giovanni Paolini, Alessandro Chiuso, Stefano Soatto
After modeling the signals, we use an anomaly detection system based on the classic CUMSUM algorithm and a variational approximation of the $f$-divergence to detect both isolated point anomalies and change-points in statistics of the signals.
no code implementations • 3 Mar 2021 • Jon McCammond, Giovanni Paolini
In particular, we show that an isometry is a product of positive reflections if and only if its spinor norm is positive.
Group Theory
1 code implementation • ICLR 2021 • Hrayr Harutyunyan, Alessandro Achille, Giovanni Paolini, Orchid Majumder, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto
We define a notion of information that an individual sample provides to the training of a neural network, and we specialize it to measure both how much a sample informs the final weights and how much it informs the function computed by the weights.
1 code implementation • ICLR 2021 • Giovanni Paolini, Ben Athiwaratkun, Jason Krone, Jie Ma, Alessandro Achille, Rishita Anubhai, Cicero Nogueira dos santos, Bing Xiang, Stefano Soatto
We propose a new framework, Translation between Augmented Natural Languages (TANL), to solve many structured prediction language tasks including joint entity and relation extraction, nested named entity recognition, relation classification, semantic role labeling, event extraction, coreference resolution, and dialogue state tracking.
Ranked #3 on Relation Classification on TACRED
no code implementations • 29 May 2019 • Alessandro Achille, Giovanni Paolini, Stefano Soatto
We establish a novel relation between the information in the weights and the effective information in the activations, and use this result to show that models with low (information) complexity not only generalize better, but are bound to learn invariant representations of future inputs.
no code implementations • 5 Apr 2019 • Alessandro Achille, Giovanni Paolini, Glen Mbeng, Stefano Soatto
Our framework is the first to measure complexity in a way that accounts for the effect of the optimization scheme, which is critical in Deep Learning.
1 code implementation • 8 Oct 2018 • Emanuele Delucchi, Linard Hoessly, Giovanni Paolini
We answer two questions raised by Bryant, Francis and Steel in their work on consensus methods in phylogenetics.
1 code implementation • 5 Sep 2017 • Giovanni Paolini
In all finite and affine cases, we are able to construct Morse matchings of a special type (we call them "precise matchings").
Algebraic Topology Combinatorics Group Theory