Publications

Sharpness-Aware Training for Accurate Inference on Noisy DNN Accelerators
Goncalo Mordido
A. Chandar
Franccois Leduc-Primeau
Energy-efficient deep neural network (DNN) accelerators are prone to non-idealities that degrade DNN performance at inference time. To miti… (see more)gate such degradation, existing methods typically add perturbations to the DNN weights during training to simulate inference on noisy hardware. However, this often requires knowledge about the target hardware and leads to a trade-off between DNN performance and robustness, decreasing the former to increase the latter. In this work, we show that applying sharpness-aware training by optimizing for both the loss value and the loss sharpness significantly improves robustness to noisy hardware at inference time while also increasing DNN performance. We further motivate our results by showing a high correlation between loss sharpness and model robustness. We show superior performance compared to injecting noise during training and aggressive weight clipping on multiple architectures, optimizers, datasets, and training regimes without relying on any assumptions about the target hardware. This is observed on a generic noise model as well as on accurate noise simulations from real hardware.
2021-12-31
arXiv.org (preprint)
doi.org
Single Allocation Hub Location with Heterogeneous Economies of Scale
Borzou Rostami
Masoud Chitsaz
Okan Arslan
Gilbert Laporte
Andrea Lodi
The economies of scale in hub location is usually modeled by a constant parameter, which captures the benefits companies obtain through cons… (see more)olidation. In their article “Single allocation hub location with heterogeneous economies of scale,” Rostami et al. relax this assumption and consider hub-hub connection costs as piecewise linear functions of the flow amounts. This spoils the triangular inequality property of the distance matrix, making the classical flow-based model invalid and further complicates the problem. The authors tackle the challenge by building a mixed-integer quadratically constrained program and by developing a methodology based on constructing Lagrangian function, linear dual functions, and specialized polynomial-time algorithms to generate enhanced cuts. The developed method offers a new strategy in Benders-type decomposition through relaxing a set of complicating constraints in subproblems when such relaxation is tight. The results confirm the efficacy of the solution methods in solving large-scale problem instances.
2021-12-31
Operations Research (published)
doi.org
Sociotechnical Harms: Scoping a Taxonomy for Harm Reduction
Renee Shelby
Shalaleh Rismani
Kathryn Henne
AJung Moon
Negar Rostamzadeh
Paul Nicholas
N'mah Fodiatu Yilla
Jess Gallegos
Andrew J Smart
Emilio Garcia
Gurleen Virk
2021-12-31
arXiv.org (preprint)
doi.org
Source-summary Entity Aggregation in Abstractive Summarization.
José-ángel González
Annie Priyadarshini Louis
Jackie CK Cheung
2021-12-31
COLING (published)
dblp.uni-trier.de
Structuring Representations Using Group Invariants
Mehran Shakerinava
Arnab Kumar Mondal
Siamak Ravanbakhsh
2021-12-31
Advances in Neural Information Processing Systems 35 (NeurIPS 2022) (published)
openreview.net
openreview.net
Summarizing Societies: Agent Abstraction in Multi-Agent Reinforcement Learning
Maximilian Puelma Touzel
Matthew D Riemer
Rupali Bhati
Irina Rish
Agents cannot make sense of many-agent societies through direct consideration of small-scale, low-level agent identities, but instead must r… (see more)ecognize emergent collective identities. Here, we take a first step towards a framework for recognizing this structure in large groups of low-level agents so that they can be modeled as a much smaller number of high-level agents—a process that we call agent abstraction. We illustrate this process by extending bisimulation metrics for state abstraction in reinforcement learning to the setting of multi-agent reinforcement learning and analyze a straightforward, if crude, abstraction based on experienced joint actions. It addresses non-stationarity due to other learning agents by improving minimax regret by a intuitive factor. To test if this compression factor provides signal for higher-level agency, we applied it to a large dataset of human play of the popular social dilemma game Diplomacy. We find that it correlates strongly with the degree of ground-truth abstraction of low-level units into the human players.
2021-12-31
(published)
openreview.net
openreview.net
A Synchro-Set-Aided Breadth-First Sphere Decoder for Polar-Coded MIMO Systems
Huayi Zhou
Xiangyun Deng
Yiqian Cai
Yifei Shen
Minhua Yang
Warren J. Gross
Xiaohu You
Chuan Zhang
The joint optimization of multiple-input-multiple-output (MIMO) detection and polar decoding has become a research hotspot for future commun… (see more)ication systems. The error-correction performance of the separate detection and decoding (SDD) is far from the Shannon capacity, which cannot meet the requirements of communication scenarios such as ultra-reliable and low latency communications (URLLC). The existing joint detection and decoding (JDD) using breadth-first sphere decoding (BFSD) improves the reliability over SDD but still has a huge performance loss on low-rate codes. In this paper, JDD using synchro-set-aided BFSD (SA-BFSD) is proposed to greatly improve the error-correction performance for polar-coded MIMO systems. We first propose a method to generate the symbol synchro sets through the concept of frozen symbols, then refine the symbol synchro sets based on the characteristics analysis of the channel matrix. We optimize the enumerating order of the symbols and reduce the enumerating levels. The frame error rate (FER) and the bit error rate of the proposed algorithms are significantly improved especially for the low-rate codes. The proposed SA-BFSD JDD achieves an up to 7.8 dB performance gain over BFSD at FER
2021-12-31
IEEE Transactions on Signal Processing (published)
doi.org
TACTiS: Transformer-Attentional Copulas for Time Series
Alexandre Drouin
Étienne Marcotte
Nicolas Chapados
The estimation of time-varying quantities is a fundamental component of decision making in fields such as healthcare and finance. However, t… (see more)he practical utility of such estimates is limited by how accurately they quantify predictive uncertainty. In this work, we address the problem of estimating the joint predictive distribution of high-dimensional multivariate time series. We propose a versatile method, based on the transformer architecture, that estimates joint distributions using an attention-based decoder that provably learns to mimic the properties of non-parametric copulas. The resulting model has several desirable properties: it can scale to hundreds of time series, supports both forecasting and interpolation, can handle unaligned and non-uniformly sampled data, and can seamlessly adapt to missing data during training. We demonstrate these properties empirically and show that our model produces state-of-the-art predictions on multiple real-world datasets.
2021-12-31
ICML (published)
proceedings.mlr.press
proceedings.mlr.press
TaHiD: Tackling Data Hiding in Fake News Detection with News Propagation Networks
Adrien Benamira
Benjamin Devillers
Etienne Lesot
Ayush K. Ray
Manal Saadi
Fragkiskos D 587
Steven Bird
Ewan Klein
Edward Loper
Nat-593
Carlos Castillo
Marcelo Mendoza
Barbara Poblete
Daryna Dementieva
Alexander Panchenko
Jacob Devlin
Ming-Wei Chang
Kenton Lee
Ashish Vaswani
Noam M. Shazeer … (see 8 more)
Niki Parmar
Adriana Romero
Pietro Lio’
Yoshua Bengio
Yaqing Wang
Fenglong Ma
Zhiwei Jin
Ye Yuan
Fake news with detrimental societal effects has 001 attracted extensive attention and research. De-002 spite early success, the state-of-the… (see more)-art meth-003 ods fall short of considering the propagation 004 of news. News propagates at different times 005 through different mediums, including users, 006 comments, and sources, which form the news 007 propagation network. Moreover, the serious 008 problem of data hiding arises, which means 009 that fake news publishers disguise fake news 010 as real to confuse users by deleting comments 011 that refute the rumor or deleting the news itself 012 when it has been spread widely. Existing meth-013 ods do not consider the propagation of news 014 and fail to identify what matters in the process, 015 which leads to fake news hiding in the prop-016 agation network and escaping from detection. 017 Inspired by the propagation of news, we pro-018 pose a novel fake news detection framework 019 named TaHiD, which models the propagation 020 as a heterogeneous dynamic graph and contains 021 the propagation attention module to measure 022 the influence of different propagation. Exper-023 iments demonstrate that TaHiD extracts use-024 ful information from the news propagation net-025 work and outperforms state-of-the-art methods 026 on several benchmark datasets for fake news 027 detection. Additional studies also show that 028 TaHiD is capable of identifying fake news in 029 the case of data hiding. 030
2021-12-31
(published)
www.semanticscholar.org
Task-Agnostic Continual Reinforcement Learning: In Praise of a Simple Baseline
Massimo Caccia
Jonas Mueller
Taesup Kim
Laurent Charlin
Rasool Fakoor
We study task-agnostic continual reinforcement learning (TACRL) in which standard RL challenges are compounded with partial observability st… (see more)emming from task agnosticism, as well as additional difficulties of continual learning (CL), i.e., learning on a non-stationary sequence of tasks. Here we compare TACRL methods with their soft upper bounds prescribed by previous literature: multi-task learning (MTL) methods which do not have to deal with non-stationary data distributions, as well as task-aware methods, which are allowed to operate under full observability . We consider a previously unexplored and straightforward baseline for TACRL, replay-based recurrent RL (3RL), in which we augment an RL algorithm with recurrent mechanisms to address partial observability and experience replay mechanisms to address catastrophic forgetting in CL. Studying empirical performance in a sequence of RL tasks, we find surprising occurrences of 3RL matching and overcoming the MTL and task-aware soft upper bounds. We lay out hypotheses that could explain this inflection point of continual and task-agnostic learning research. Our hypotheses are empirically tested in continuous control tasks via a large-scale study of the popular multi-task and continual learning benchmark Meta-World. By analyzing different training statistics including gradient conflict, we find evidence that 3RL’s outperformance stems from its ability to quickly infer how new tasks relate with the previous ones, enabling forward transfer.
2021-12-31
arXiv.org (preprint)
doi.org
Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning
Aniket Didolkar
Kshitij Gupta
Anirudh Goyal
Nitesh B. Gundavarapu
Alex Lamb
Nan Rosemary Ke
Yoshua Bengio
Recurrent neural networks have a strong inductive bias towards learning temporally compressed representations, as the entire history of a se… (see more)quence is represented by a single vector. By contrast, Transformers have little inductive bias towards learning temporally compressed representations, as they allow for attention over all previously computed elements in a sequence. Having a more compressed representation of a sequence may be beneficial for generalization, as a high-level representation may be more easily re-used and re-purposed and will contain fewer irrelevant details. At the same time, excessive compression of representations comes at the cost of expressiveness. We propose a solution which divides computation into two streams. A slow stream that is recurrent in nature aims to learn a specialized and compressed representation, by forcing chunks of
2021-12-31
Advances in Neural Information Processing Systems 35 (NeurIPS 2022) (published)
doi.org
openreview.net
On the benefits of representation regularization in invariance based domain generalization
Changjian Shui
Boyu Wang
Christian Gagné
A crucial aspect of reliable machine learning is to design a deployable system for generalizing new related but unobserved environments. Dom… (see more)ain generalization aims to alleviate such a prediction gap between the observed and unseen environments. Previous approaches commonly incorporated learning the invariant representation for achieving good empirical performance. In this paper, we reveal that merely learning the invariant representation is vulnerable to the related unseen environment. To this end, we derive a novel theoretical analysis to control the unseen test environment error in the representation learning, which highlights the importance of controlling the smoothness of representation. In practice, our analysis further inspires an efficient regularization method to improve the robustness in domain generalization. The proposed regularization is orthogonal to and can be straightforwardly adopted in existing domain generalization algorithms that ensure invariant representation learning. Empirical results show that our algorithm outperforms the base versions in various datasets and invariance criteria.
2021-12-31
Machine Learning (published)
doi.org
arxiv.org