Robust Data-driven Prescriptiveness Optimization
Mehran Poursoltani
Angelos Georghiou
The abundance of data has led to the emergence of a variety of optimization techniques that attempt to leverage available side information t… (see more)o provide more anticipative decisions. The wide range of methods and contexts of application have motivated the design of a universal unitless measure of performance known as the coefficient of prescriptiveness. This coefficient was designed to quantify both the quality of contextual decisions compared to a reference one and the prescriptive power of side information. To identify policies that maximize the former in a data-driven context, this paper introduces a distributionally robust contextual optimization model where the coefficient of prescriptiveness substitutes for the classical empirical risk minimization objective. We present a bisection algorithm to solve this model, which relies on solving a series of linear programs when the distributional ambiguity set has an appropriate nested form and polyhedral structure. Studying a contextual shortest path problem, we evaluate the robustness of the resulting policies against alternative methods when the out-of-sample dataset is subject to varying amounts of distribution shift.
A Scalable Architecture for Future Regenerative Satellite Payloads
Olfa Ben Yahia
Zineb Garroussi
Brunilde Sansò
Jean-François Frigon
Stéphane Martel
Gunes Karabulut Kurt
This paper addresses the limitations of current satellite payload architectures, which are predominantly hardware-driven and lack the flexib… (see more)ility to adapt to increasing data demands and uneven traffic. To overcome these challenges, we present a novel architecture for future regenerative and programmable satellite payloads and utilize interconnected modem banks to promote higher scalability and flexibility. We formulate an optimization problem to efficiently manage traffic among these modem banks and balance the load. Additionally, we provide comparative numerical simulation results, considering end-to-end delay and packet loss analysis. The results illustrate that our proposed architecture maintains lower delays and packet loss even with higher traffic demands and smaller buffer sizes.
A Scalable Architecture for Future Regenerative Satellite Payloads
Olfa Ben Yahia
Zineb Garroussi
Brunilde Sansò
Jean-François Frigon
Stéphane Martel
Gunes Karabulut Kurt
This paper addresses the limitations of current satellite payload architectures, which are predominantly hardware-driven and lack the flexib… (see more)ility to adapt to increasing data demands and uneven traffic. To overcome these challenges, we present a novel architecture for future regenerative and programmable satellite payloads and utilize interconnected modem banks to promote higher scalability and flexibility. We formulate an optimization problem to efficiently manage traffic among these modem banks and balance the load. Additionally, we provide comparative numerical simulation results, considering end-to-end delay and packet loss analysis. The results illustrate that our proposed architecture maintains lower delays and packet loss even with higher traffic demands and smaller buffer sizes.
A Scalable Architecture for Future Regenerative Satellite Payloads
Olfa Ben Yahia
Zineb Garroussi
Brunilde Sansò
Jean-François Frigon
Stéphane Martel
Gunes Karabulut Kurt
This paper addresses the limitations of current satellite payload architectures, which are predominantly hardware-driven and lack the flexib… (see more)ility to adapt to increasing data demands and uneven traffic. To overcome these challenges, we present a novel architecture for future regenerative and programmable satellite payloads and utilize interconnected modem banks to promote higher scalability and flexibility. We formulate an optimization problem to efficiently manage traffic among these modem banks and balance the load. Additionally, we provide comparative numerical simulation results, considering end-to-end delay and packet loss analysis. The results illustrate that our proposed architecture maintains lower delays and packet loss even with higher traffic demands and smaller buffer sizes.
SelfIE: Self-Interpretation of Large Language Model Embeddings
Haozhe Chen
Carl Vondrick
Chengzhi Mao
Simple and Scalable Strategies to Continually Pre-train Large Language Models
Adam Ibrahim
Benjamin Thérien
Kshitij Gupta
Mats Leon Richter
Quentin Gregory Anthony
Timothee LESORT
SiT: Symmetry-invariant Transformers for Generalisation in Reinforcement Learning
Matthias Weissenbacher
Yoshinobu Kawahara
An open challenge in reinforcement learning (RL) is the effective deployment of a trained policy to new or slightly different situations as … (see more)well as semantically-similar environments. We introduce Symmetry-Invariant Transformer (SiT), a scalable vision transformer (ViT) that leverages both local and global data patterns in a self-supervised manner to improve generalisation. Central to our approach is Graph Symmetric Attention, which refines the traditional self-attention mechanism to preserve graph symmetries, resulting in invariant and equivariant latent representations. We showcase SiT’s superior generalization over ViTs on MiniGrid and Procgen RL benchmarks, and its sample efficiency on Atari 100k and CIFAR10.
Stealing part of a production language model
Nicholas Carlini
Daniel Paleka
Krishnamurthy Dj Dvijotham
Thomas Steinke
Jonathan Hayase
A. Feder Cooper
Katherine Lee
Matthew Jagielski
Milad Nasr
Arthur Conmy
Eric Wallace
Florian Tramèr
We introduce the first model-stealing attack that extracts precise, nontrivial information from black-box production language models like … (see more)OpenAI's ChatGPT or Google's PaLM-2. Specifically, our attack recovers the embedding projection layer (up to symmetries) of a transformer model, given typical API access. For under \\
Stochastic positional embeddings improve masked image modeling
Amir Bar
Florian Bordes
Assaf Shocher
Mahmoud Assran
Nicolas Ballas
Trevor Darrell
Amir Globerson
Yann LeCun
Stop Regressing: Training Value Functions via Classification for Scalable Deep RL
Jesse Farebrother
Jordi Orbay
Quan Vuong
Adrien Ali Taiga
Yevgen Chebotar
Ted Xiao
Alex Irpan
Sergey Levine
Aleksandra Faust
Aviral Kumar
Value functions are an essential component in deep reinforcement learning (RL), that are typically trained via mean squared error regression… (see more) to match bootstrapped target values. However, scaling value-based RL methods to large networks has proven challenging. This difficulty is in stark contrast to supervised learning: by leveraging a cross-entropy classification loss, supervised methods have scaled reliably to massive networks. Observing this discrepancy, in this paper, we investigate whether the scalability of deep RL can also be improved simply by using classification in place of regression for training value functions. We show that training value functions with categorical cross-entropy significantly enhances performance and scalability across various domains, including single-task RL on Atari 2600 games, multi-task RL on Atari with large-scale ResNets, robotic manipulation with Q-transformers, playing Chess without search, and a language-agent Wordle task with high-capacity Transformers, achieving state-of-the-art results on these domains. Through careful analysis, we show that categorical cross-entropy mitigates issues inherent to value-based RL, such as noisy targets and non-stationarity. We argue that shifting to categorical cross-entropy for training value functions can substantially improve the scalability of deep RL at little-to-no cost.
A Tale of Tails: Model Collapse as a Change of Scaling Laws
Yunzhen Feng
Pu Yang
Francois Charton
Julia Kempe
As AI model size grows, neural scaling laws have become a crucial tool to predict the improvements of large models when increasing … (see more)capacity and the size of original (human or natural) training data. Yet, the widespread use of popular models means that the ecosystem of online data and text will co-evolve to progressively contain increased amounts of synthesized data. In this paper we ask: How will the scaling laws change in the inevitable regime where synthetic data makes its way into the training corpus? Will future models, still improve, or be doomed to degenerate up to total (model) collapse? We develop a theoretical framework of model collapse through the lens of scaling laws. We discover a wide range of decay phenomena, analyzing loss of scaling, shifted scaling with number of generations, the ”un-learning" of skills, and grokking when mixing human and synthesized data. Our theory is validated by large-scale experiments with a transformer on an arithmetic task and text generation using the large language model Llama2.
The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks
Ziquan Liu
Yufei Cui
Yan Yan
Yi Xu
Xiangyang Ji
Antoni B. Chan
In safety-critical applications such as medical imaging and autonomous driving, where decisions have profound implications for patient healt… (see more)h and road safety, it is imperative to maintain both high adversarial robustness to protect against potential adversarial attacks and reliable uncertainty quantification in decision-making. With extensive research focused on enhancing adversarial robustness through various forms of adversarial training (AT), a notable knowledge gap remains concerning the uncertainty inherent in adversarially trained models. To address this gap, this study investigates the uncertainty of deep learning models by examining the performance of conformal prediction (CP) in the context of standard adversarial attacks within the adversarial defense community. It is first unveiled that existing CP methods do not produce informative prediction sets under the commonly used