Welcome to ShortScience.org! |

- ShortScience.org is a platform for post-publication discussion aiming to improve accessibility and reproducibility of research ideas.
- The website has 1567 public summaries, mostly in machine learning, written by the community and organized by paper, conference, and year.
- Reading summaries of papers is useful to obtain the perspective and insight of another reader, why they liked or disliked it, and their attempt to demystify complicated sections.
- Also, writing summaries is a good exercise to understand the content of a paper because you are forced to challenge your assumptions when explaining it.
- Finally, you can keep up to date with the flood of research by reading the latest summaries on our Twitter and Facebook pages.

Thwarting Adversarial Examples: An L_0-Robust Sparse Fourier Transform

Bafna, Mitali and Murtagh, Jack and Vyas, Nikhil

Neural Information Processing Systems Conference - 2018 via Local Bibsonomy

Keywords: dblp

Bafna, Mitali and Murtagh, Jack and Vyas, Nikhil

Neural Information Processing Systems Conference - 2018 via Local Bibsonomy

Keywords: dblp

[link]
Bafna et al. show that iterative hard thresholding results in $L_0$ robust Fourier transforms. In particular, as shown in Algorithm 1, iterative hard thresholding assumes a signal $y = x + e$ where $x$ is assumed to be sparse, and $e$ is assumed to be sparse. This translates to noise $e$ that is bounded in its $L_0$ norm, corresponding to common adversarial attacks such as adversarial patches in computer vision. Using their algorithm, the authors can provably reconstruct the signal, specifically the top-$k$ coordinates for a $k$-sparse signal, which can subsequently be fed to a neural network classifier. In experiments, the classifier is always trained on sparse signals, and at test time, the sparse signal is reconstructed prior to the forward pass. This way, on MNIST and Fashion-MNIST, the algorithm is able to recover large parts of the original accuracy. https://i.imgur.com/yClXLoo.jpg Algorithm 1 (see paper for details): The iterative hard thresholding algorithm resulting in provable robustness against $L_0$ attack on images and other signals. Also find this summary at [davidstutz.de](https://davidstutz.de/category/reading/). |

Communication-Efficient Learning of Deep Networks from Decentralized Data

McMahan, H. Brendan and Moore, Eider and Ramage, Daniel and Hampson, Seth and Arcas, Blaise Agüera y

- 2016 via Local Bibsonomy

Keywords: distributed, deep_learning, hpc

McMahan, H. Brendan and Moore, Eider and Ramage, Daniel and Hampson, Seth and Arcas, Blaise Agüera y

- 2016 via Local Bibsonomy

Keywords: distributed, deep_learning, hpc

[link]
Federated learning is the problem of training a model that incorporates updates from the data of many individuals, without having direct access to that data, or having to store it. This is potentially desirable both for reasons of privacy (not wanting to have access to private data in a centralized way), and for potential benefits to transport cost when data needed to train models exists on a user's device, and would require a lot of bandwidth to transfer to a centralized server. Historically, the default way to do Federated Learning was with an algorithm called FedSGD, which worked by: - Sending a copy of the current model to each device/client - Calculating a gradient update to be applied on top of that current model given a batch of data sampled from the client's device - Sending that gradient back to the central server - Averaging those gradients and applying them all at once to a central model The authors note that this approach is equivalent to one where a single device performs a step of gradient descent locally, sends the resulting *model* back to the the central server, and performs model averaging by averaging the parameter vectors there. Given that, and given their observation that, in federated learning, communication of gradients and models is generally much more costly than the computation itself (since the computation happens across so many machines), they ask whether the communication required to get to a certain accuracy could be better optimized by performing multiple steps of gradient calculation and update on a given device, before sending the resulting model back to a central server to be average with other clients models. Specifically, their algorithm, FedAvg, works by: - Dividing the data on a given device into batches of size B - Calculating an update on each batch and applying them sequentially to the starting model sent over the wire from the server - Repeating this for E epochs Conceptually, this should work perfectly well in the world where data from each batch is IID - independently drawn from the same distribution. But that is especially unlikely to be true in the case of federated learning, when a given user and device might have very specialized parts of the data space, and prior work has shown that there exist pathological cases where averaged models can perform worse than either model independently, even *when* the IID condition is met. The authors experiment empirically ask the question whether these sorts of pathological cases arise when simulating a federated learning procedure over MNIST and a language model trained on Shakespeare, trying over a range of hyperparameters (specifically B and E), and testing the case where data is heavily non-IID (in their case: where different "devices" had non-overlapping sets of digits). https://i.imgur.com/xq9vi8S.png They show that, in both the IID and non-IID settings, they are able to reach their target accuracy, and are able to do so with many fewer rounds of communciation than are required by FedSGD (where an update is sent over the wire, and a model sent back, for each round of calculation done on the device.) The authors argue that this shows the practical usefulness of a Federated Learning approach that does more computation on individual devices before updating, even in the face of theoretical pathological cases. |

Understanding deep learning requires rethinking generalization

Chiyuan Zhang and Samy Bengio and Moritz Hardt and Benjamin Recht and Oriol Vinyals

arXiv e-Print archive - 2016 via Local arXiv

Keywords: cs.LG

**First published:** 2016/11/10 (6 years ago)

**Abstract:** Despite their massive size, successful deep artificial neural networks can
exhibit a remarkably small difference between training and test performance.
Conventional wisdom attributes small generalization error either to properties
of the model family, or to the regularization techniques used during training.
Through extensive systematic experiments, we show how these traditional
approaches fail to explain why large neural networks generalize well in
practice. Specifically, our experiments establish that state-of-the-art
convolutional networks for image classification trained with stochastic
gradient methods easily fit a random labeling of the training data. This
phenomenon is qualitatively unaffected by explicit regularization, and occurs
even if we replace the true images by completely unstructured random noise. We
corroborate these experimental findings with a theoretical construction showing
that simple depth two neural networks already have perfect finite sample
expressivity as soon as the number of parameters exceeds the number of data
points as it usually does in practice.
We interpret our experimental findings by comparison with traditional models.
more
less

Chiyuan Zhang and Samy Bengio and Moritz Hardt and Benjamin Recht and Oriol Vinyals

arXiv e-Print archive - 2016 via Local arXiv

Keywords: cs.LG

[link]
This paper deals with the question what / how exactly CNNs learn, considering the fact that they usually have more trainable parameters than data points on which they are trained. When the authors write "deep neural networks", they are talking about Inception V3, AlexNet and MLPs. ## Key contributions * Deep neural networks easily fit random labels (achieving a training error of 0 and a test error which is just randomly guessing labels as expected). $\Rightarrow$Those architectures can simply brute-force memorize the training data. * Deep neural networks fit random images (e.g. Gaussian noise) with 0 training error. The authors conclude that VC-dimension / Rademacher complexity, and uniform stability are bad explanations for generalization capabilities of neural networks * The authors give a construction for a 2-layer network with $p = 2n+d$ parameters - where $n$ is the number of samples and $d$ is the dimension of each sample - which can easily fit any labeling. (Finite sample expressivity). See section 4. ## What I learned * Any measure $m$ of the generalization capability of classifiers $H$ should take the percentage of corrupted labels ($p_c \in [0, 1]$, where $p_c =0$ is a perfect labeling and $p_c=1$ is totally random) into account: If $p_c = 1$, then $m()$ should be 0, too, as it is impossible to learn something meaningful with totally random labels. * We seem to have built models which work well on image data in general, but not "natural" / meaningful images as we thought. ## Funny > deep neural nets remain mysterious for many reasons > Note that this is not exactly simple as the kernel matrix requires 30GB to store in memory. Nonetheless, this system can be solved in under 3 minutes in on a commodity workstation with 24 cores and 256 GB of RAM with a conventional LAPACK call. ## See also * [Deep Nets Don't Learn Via Memorization](https://openreview.net/pdf?id=rJv6ZgHYg) |

When Does Contrastive Visual Representation Learning Work?

Elijah Cole and Xuan Yang and Kimberly Wilber and Oisin Mac Aodha and Serge Belongie

arXiv e-Print archive - 2021 via Local arXiv

Keywords: cs.CV, cs.LG

**First published:** 2023/02/01 (just now)

**Abstract:** Recent self-supervised representation learning techniques have largely closed
the gap between supervised and unsupervised learning on ImageNet
classification. While the particulars of pretraining on ImageNet are now
relatively well understood, the field still lacks widely accepted best
practices for replicating this success on other datasets. As a first step in
this direction, we study contrastive self-supervised learning on four diverse
large-scale datasets. By looking through the lenses of data quantity, data
domain, data quality, and task granularity, we provide new insights into the
necessary conditions for successful self-supervised learning. Our key findings
include observations such as: (i) the benefit of additional pretraining data
beyond 500k images is modest, (ii) adding pretraining images from another
domain does not lead to more general representations, (iii) corrupted
pretraining images have a disparate impact on supervised and self-supervised
pretraining, and (iv) contrastive learning lags far behind supervised learning
on fine-grained visual classification tasks.
more
less

Elijah Cole and Xuan Yang and Kimberly Wilber and Oisin Mac Aodha and Serge Belongie

arXiv e-Print archive - 2021 via Local arXiv

Keywords: cs.CV, cs.LG

[link]
This is a mildly silly paper to summarize, since there isn't really a new mechanism to understand, but rather a number of straightforward (and interesting!) empirical results that are also quite well-explained in the paper itself. That said, for the sake of a tiny bit more brevity than the paper itself provides, I'll try to pull out some of the conclusions I found the most interesting here. The general goal of this paper is to better understand the contours of when self-supervised representation learning is valuable for vision (and specifically when it can compete with supervised learning), and when it doesn't. In general, the results are all using ResNet backbones, with SimCLR SSL, on image classification datasets. Some bullet-point takeaways: - The SSL models being tested here seem to roughly saturate at unsupervised dataset sizes of around 500K; the comparative jump from dataset sizes of 500K to 1M is fairly small. - Once you have a supervised dataset of around 50K or more, the benefit of SSL pretraining starts to diminish, and it converges to being more similar to just supervised learning on that numbrer of labeled images. On the flip side, it's only possible to get close to "good" fully supervised performance by using 100K images or more on top of a SSL baseline. - Even within image classification datasets, it's much better to do SSL representation on the same dataset as the one you'll use for downstream training; trying to transfer representations to different datasets leads to meaningfully worse results. Interestingly, this is even true when you add out-of-domain (i.e. other-dataset) data to an existing in-domain dataset: a dataset of 250K in-dataset images does better than a 500K dataset of images from mixed datasets, and does notably better than a 1M dataset of mixed images. In this case, adding more out-of-domain images seems to have just degraded performance - SSL seems to perform more closely to SL on a course label set; when the label set gets more granular, the task gets harder overall, but, more specifically, the gap between SSL and SL grows - When the authors tried different forms of dataset corruption, SSL was much more robust to adding salt-and-pepper noise than it was to removing high-frequency information in the form of reducing the images to a lower resolution. |

Behavior Regularized Offline Reinforcement Learning

Wu, Yifan and Tucker, George and Nachum, Ofir

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Wu, Yifan and Tucker, George and Nachum, Ofir

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

[link]
Wu et al. provide a framework (behavior regularized actor critic (BRAC)) which they use to empirically study the impact of different design choices in batch reinforcement learning (RL). Specific instantiations of the framework include BCQ, KL-Control and BEAR. Pure off-policy rl describes the problem of learning a policy purely from a batch $B$ of one step transitions collected with a behavior policy $\pi_b$. The setting allows for no further interactions with the environment. This learning regime is for example in high stake scenarios, like education or heath care, desirable. The core principle of batch RL-algorithms in to stay in some sense close to the behavior policy. The paper proposes to incorporate this firstly via a regularization term in the value function, which is denoted as **value penalty**. In this case the value function of BRAC takes the following form: $ V_D^{\pi}(s) = \sum_{t=0}^{\infty} \gamma ^t \mathbb{E}_{s_t \sim P_t^{\pi}(s)}[R^{pi}(s_t)- \alpha D(\pi(\cdot\vert s_t) \Vert \pi_b(\cdot \vert s_t)))], $ where $\pi_b$ is the maximum likelihood estimate of the behavior policy based upon $B$. This results in a Q-function objective: $\min_{Q} = \mathbb{E}_{\substack{(s,a,r,s') \sim D \\ a' \sim \pi_{\theta}(\cdot \vert s)}}\left[(r + \gamma \left(\bar{Q}(s',a')-\alpha D(\pi(\cdot\vert s) \Vert \pi_b(\cdot \vert s) \right) - Q(s,a) \right] $ and the corresponding policy update: $ \max_{\pi_{\theta}} \mathbb{E}_{(s,a,r,s') \sim D} \left[ \mathbb{E}_{a^{''} \sim \pi_{\theta}(\cdot \vert s)}[Q(s,a^{''})] - \alpha D(\pi(\cdot\vert s) \Vert \pi_b(\cdot \vert s) \right] $ The second approach is **policy regularization** . Here the regularization weight $\alpha$ is set for value-objectives (V- and Q) to zero and is non-zero for the policy objective. It is possible to instantiate for example the following batch RL algorithms in this setting: - BEAR: policy regularization with sample-based kernel MMD as D and min-max mixture of the two ensemble elements for $\bar{Q}$ - BCQ: no regularization but policy optimization over restricted space Extensive Experiments over the four Mujoco tasks Ant, HalfCheetah,Hopper Walker show: 1. for a BEAR like instantiation there is a modest advantage of keeping $\alpha$ fixed 2. using a mixture of a two or four Q-networks ensemble as target value yields better returns that using one Q-network 3. taking the minimum of ensemble Q-functions is slightly better than taking a mixture (for Ant, HalfCeetah & Walker, but not for Hooper 4. the use of value-penalty yields higher return than the policy-penalty 5. no choice for D (MMD, KL (primal), KL(dual) or Wasserstein (dual)) significantly outperforms the other (note that his contradicts the BEAR paper where MMD was better than KL) 6. the value penalty version consistently outperforms BEAR which in turn outperforms BCQ with improves upon a partially trained baseline. This large scale study of different design choices helps in developing new methods. It is however surprising to see, that most design choices in current methods are shown empirically to be non crucial. This points to the importance of agreeing upon common test scenarios within a community to prevent over-fitting new algorithms to a particular setting. |

About