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 1583 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.

Identity Mappings in Deep Residual Networks

He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian

European Conference on Computer Vision - 2016 via Local Bibsonomy

Keywords: dblp

He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian

European Conference on Computer Vision - 2016 via Local Bibsonomy

Keywords: dblp

[link]
This is follow-up work to the ResNets paper. It studies the propagation formulations behind the connections of deep residual networks and performs ablation experiments. A residual block can be represented with the equations $y_l = h(x_l) + F(x_l, W_l); x_{l+1} = f(y_l)$. $x_l$ is the input to the l-th unit and $x_{l+1}$ is the output of the l-th unit. In the original ResNets paper, $h(x_l) = x_l$, $f$ is ReLu, and F consists of 2-3 convolutional layers (bottleneck architecture) with BN and ReLU in between. In this paper, they propose a residual block with both $h(x)$ and $f(x)$ as identity mappings, which trains faster and performs better than their earlier baseline. Main contributions: - Identity skip connections work much better than other multiplicative interactions that they experiment with: - Scaling $(h(x) = \lambda x)$: Gradients can explode or vanish depending on whether modulating scalar \lambda > 1 or < 1. - Gating ($1-g(x)$ for skip connection and $g(x)$ for function F): For gradients to propagate freely, $g(x)$ should approach 1, but F gets suppressed, hence suboptimal. This is similar to highway networks. $g(x)$ is a 1x1 convolutional layer. - Gating (shortcut-only): Setting high biases pushes initial $g(x)$ towards identity mapping, and test error is much closer to baseline. - 1x1 convolutional shortcut: These work well for shallower networks (~34 layers), but training error becomes high for deeper networks, probably because they impede gradient propagation. - Experiments on activations. - BN after addition messes up information flow, and performs considerably worse. - ReLU before addition forces the signal to be non-negative, so the signal is monotonically increasing, while ideally a residual function should be free to take values in (-inf, inf). - BN + ReLU pre-activation works best. This also prevents overfitting, due to BN's regularizing effect. Input signals to all weight layers are normalized. ## Strengths - Thorough set of experiments to show that identity shortcut connections are easiest for the network to learn. Activation of any deeper unit can be written as the sum of the activation of a shallower unit and a residual function. This also implies that gradients can be directly propagated to shallower units. This is in contrast to usual feedforward networks, where gradients are essentially a series of matrix-vector products, that may vanish, as networks grow deeper. - Improved accuracies than their previous ResNets paper. ## Weaknesses / Notes - Residual units are useful and share the same core idea that worked in LSTM units. Even though stacked non-linear layers are capable of asymptotically approximating any arbitrary function, it is clear from recent work that residual functions are much easier to approximate than the complete function. The [latest Inception paper](http://arxiv.org/abs/1602.07261) also reports that training is accelerated and performance is improved by using identity skip connections across Inception modules. - It seems like the degradation problem, which serves as motivation for residual units, exists in the first place for non-idempotent activation functions such as sigmoid, hyperbolic tan. This merits further investigation, especially with recent work on function-preserving transformations such as [Network Morphism](http://arxiv.org/abs/1603.01670), which expands the Net2Net idea to sigmoid, tanh, by using parameterized activations, initialized to identity mappings. |

MnasNet: Platform-Aware Neural Architecture Search for Mobile

Tan, Mingxing and Chen, Bo and Pang, Ruoming and Vasudevan, Vijay and Le, Quoc V.

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

Tan, Mingxing and Chen, Bo and Pang, Ruoming and Vasudevan, Vijay and Le, Quoc V.

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

[link]
When machine learning models need to run on personal devices, that implies a very particular set of constraints: models need to be fairly small and low-latency when run on a limited-compute device, without much loss in accuracy. A number of human-designed architectures have been engineered to try to solve for these constraints (depthwise convolutions, inverted residual bottlenecks), but this paper's goal is to use Neural Architecture Search (NAS) to explicitly optimize the architecture against latency and accuracy, to hopefully find a good trade-off curve between the two. This paper isn't the first time NAS has been applied on the problem of mobile-optimized networks, but a few choices are specific to this paper. 1. Instead of just optimizing against accuracy, or optimizing against accuracy with a sharp latency requirement, the authors here construct a weighted loss that includes both accuracy and latency, so that NAS can explore the space of different trade-off points, rather than only those below a sharp threshold. 2. They design a search space where individual sections or "blocks" of the network can be configured separately, with the hope being that this flexibility helps NAS trade off complexity more strongly in the early parts of the network, where, at a higher spatial resolution, it implies greater computation cost and latency, without necessary dropping that complexity later in the network, where it might be lower-cost. Blocks here are specified by the type of convolution op, kernel size, squeeze-and-excitation ratio, use of a skip op, output filter size, and the number of times an identical layer of this construction will be repeated to constitute a block. Mechanically, models are specified as discrete strings of tokens (a block is made up of tokens indicating its choices along these design axes, and a model is made up of multiple blocks). These are represented in a RL framework, where a RNN model sequentially selects tokens as "actions" until it gets to a full model specification . This is repeated multiple times to get a batch of models, which here functions analogously to a RL episode. These models are then each trained for only five epochs (it's desirable to use a full-scale model for accurate latency measures, but impractical to run its full course of training). After that point, accuracy is calculated, and latency determined by running the model on an actual Pixel phone CPU. These two measures are weighted together to get a reward, which is used to train the RNN model-selection model using PPO. https://i.imgur.com/dccjaqx.png Across a few benchmarks, the authors show that models found with MNasNet optimization are able to reach parts of the accuracy/latency trade-off curve that prior techniques had not. |

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Ioffe, Sergey and Szegedy, Christian

International Conference on Machine Learning - 2015 via Local Bibsonomy

Keywords: dblp

Ioffe, Sergey and Szegedy, Christian

International Conference on Machine Learning - 2015 via Local Bibsonomy

Keywords: dblp

[link]
The main contribution of this paper is introducing a new transformation that the authors call Batch Normalization (BN). The need for BN comes from the fact that during the training of deep neural networks (DNNs) the distribution of each layer’s input change. This phenomenon is called internal covariate shift (ICS). #### What is BN? Normalize each (scalar) feature independently with respect to the mean and variance of the mini batch. Scale and shift the normalized values with two new parameters (per activation) that will be learned. The BN consists of making normalization part of the model architecture. #### What do we gain? According to the author, the use of BN provides a great speed up in the training of DNNs. In particular, the gains are greater when it is combined with higher learning rates. In addition, BN works as a regularizer for the model which allows to use less dropout or less L2 normalization. Furthermore, since the distribution of the inputs is normalized, it also allows to use sigmoids as activation functions without the saturation problem. #### What follows? This seems to be specially promising for training recurrent neural networks (RNNs). The vanishing and exploding gradient problems \cite{journals/tnn/BengioSF94} have their origin in the iteration of transformation that scale up or down the activations in certain directions (eigenvectors). It seems that this regularization would be specially useful in this context since this would allow the gradient to flow more easily. When we unroll the RNNs, we usually have ultra deep networks. #### Like * Simple idea that seems to improve training. * Makes training faster. * Simple to implement. Probably. * You can be less careful with initialization. #### Dislike * Does not work with stochastic gradient descent (minibatch size = 1). * This could reduce the parallelism of the algorithm since now all the examples in a mini batch are tied. * Results on ensemble of networks for ImageNet makes it harder to evaluate the relevance of BN by itself. (Although they do mention the performance of a single model). |

Critic Regularized Regression

Ziyu Wang and Alexander Novikov and Konrad Zolna and Jost Tobias Springenberg and Scott Reed and Bobak Shahriari and Noah Siegel and Josh Merel and Caglar Gulcehre and Nicolas Heess and Nando de Freitas

arXiv e-Print archive - 2020 via Local arXiv

Keywords: cs.LG, cs.AI, stat.ML

**First published:** 2023/12/10 (just now)

**Abstract:** Offline reinforcement learning (RL), also known as batch RL, offers the
prospect of policy optimization from large pre-recorded datasets without online
environment interaction. It addresses challenges with regard to the cost of
data collection and safety, both of which are particularly pertinent to
real-world applications of RL. Unfortunately, most off-policy algorithms
perform poorly when learning from a fixed dataset. In this paper, we propose a
novel offline RL algorithm to learn policies from data using a form of
critic-regularized regression (CRR). We find that CRR performs surprisingly
well and scales to tasks with high-dimensional state and action spaces --
outperforming several state-of-the-art offline RL algorithms by a significant
margin on a wide range of benchmark tasks.
more
less

Ziyu Wang and Alexander Novikov and Konrad Zolna and Jost Tobias Springenberg and Scott Reed and Bobak Shahriari and Noah Siegel and Josh Merel and Caglar Gulcehre and Nicolas Heess and Nando de Freitas

arXiv e-Print archive - 2020 via Local arXiv

Keywords: cs.LG, cs.AI, stat.ML

[link]
Offline reinforcement learning is potentially high-value thing for the machine learning community learn to do well, because there are many applications where it'd be useful to generate a learnt policy for responding to a dynamic environment, but where it'd be too unsafe or expensive to learn in an on-policy or online way, where we continually evaluate our actions in the environment to test their value. In such settings, we'd like to be able to take a batch of existing data - collected from a human demonstrator, or from some other algorithm - and be able to learn a policy from those pre-collected transitions, without being able to query the environment further by taking arbitrary actions. There are two broad strategies for learning a policy from precollected transitions. One is to simply learn to mimic the action policy used by the demonstrator, predicting the action the demonstrator would take in a given state, without making use of reward data at all. This is Behavioral Cloning, and has the advantage of being somewhat more conservative (in terms of not experimenting with possibly-unsafe-or-low-reward actions the demonstrator never took), but this is also a disadvantage, because it's not possible to get higher reward than the demonstrator themselves got if you're simply copying their behavior. Another approach is to learn a Q function - estimating the value of a given action in a given state - using the reward data from the precollected transitions. This can also have some downsides, mostly in the direction of overconfidence. Q value Temporal Difference learning works by using the current reward added to the max Q value over possible next actions as the target for the current-state Q estimate. This tends to lead to overestimates, because regression to the mean effects mean that the highest value Q estimates are disproportionately likely to be noisy (possibly because they correspond to an action with little data in the demonstrator dataset). In on-policy Q learning, this is less problematic, because the agent can take the action associated with their noisily inaccurate estimate, and as a result get more data for that action, and get an estimate that is less noisy in future. But when we're in a fully offline setting, all our learning is completed before we actually start taking actions with our policy, so taking high-uncertainty actions isn't a valuable source of new information, but just risky. The approach suggested by this DeepMind paper - Critic Regularized Regression, or CRR - is essentially a synthesis of these two possible approaches. The method learns a Q function as normal, using temporal difference methods. The distinction in this method comes from how to get a policy, given a learned Q function. Rather than simply taking the action your Q estimate says is highest-value at a particular point, CRR optimizes a policy according to the formula shown below. The f() function is a stand-in for various potential functions, all of which are monotonic with respect to the Q function, meaning they increase when the Q function does. https://i.imgur.com/jGmhYdd.png This basically amounts to a form of a behavioral cloning loss (with the part that maximizes the probability under your policy of the actions sampled from the demonstrator dataset), but weighted or, as the paper terms it, filtered, by the learned Q function. The higher the estimated q value for a transition, the more weight is placed on that transition from the demo dataset having high probability under your policy. Rather than trying to mimic all of the actions of the demonstrator, the policy preferentially tries to mimic the demonstrator actions that it estimates were particularly high-quality. Different f() functions lead to different kinds of filtration. The `binary`version is an indicator function for the Advantage of an action (the Q value for that action at that state minus some reference value for the state, describing how much better the action is than other alternatives at that state) being greater than zero. Another, `exp`, uses exponential weightings which do a more "soft" upweighting or downweighting of transitions based on advantage, rather than the sharp binary of whether an actions advantage is above 1. The authors demonstrate that, on multiple environments from three different environment suites, CRR outperforms other off-policy baselines - either more pure behavioral cloning, or more pure RL - and in many cases does so quite dramatically. They find that the sharper binary weighting scheme does better on simpler tasks, since the trade-off of fewer but higher-quality samples to learn from works there. However, on more complex tasks, the policy benefits from the exp weighting, which still uses and learns from more samples (albeit at lower weights), which introduces some potential mimicking of lower-quality transitions, but at the trade of a larger effective dataset size to learn from. |

Nerfies: Deformable Neural Radiance Fields

Keunhong Park and Utkarsh Sinha and Jonathan T. Barron and Sofien Bouaziz and Dan B Goldman and Steven M. Seitz and Ricardo Martin-Brualla

arXiv e-Print archive - 2020 via Local arXiv

Keywords: cs.CV, cs.GR

**First published:** 2023/12/10 (just now)

**Abstract:** We present the first method capable of photorealistically reconstructing
deformable scenes using photos/videos captured casually from mobile phones. Our
approach augments neural radiance fields (NeRF) by optimizing an additional
continuous volumetric deformation field that warps each observed point into a
canonical 5D NeRF. We observe that these NeRF-like deformation fields are prone
to local minima, and propose a coarse-to-fine optimization method for
coordinate-based models that allows for more robust optimization. By adapting
principles from geometry processing and physical simulation to NeRF-like
models, we propose an elastic regularization of the deformation field that
further improves robustness. We show that our method can turn casually captured
selfie photos/videos into deformable NeRF models that allow for photorealistic
renderings of the subject from arbitrary viewpoints, which we dub "nerfies." We
evaluate our method by collecting time-synchronized data using a rig with two
mobile phones, yielding train/validation images of the same pose at different
viewpoints. We show that our method faithfully reconstructs non-rigidly
deforming scenes and reproduces unseen views with high fidelity.
more
less

Keunhong Park and Utkarsh Sinha and Jonathan T. Barron and Sofien Bouaziz and Dan B Goldman and Steven M. Seitz and Ricardo Martin-Brualla

arXiv e-Print archive - 2020 via Local arXiv

Keywords: cs.CV, cs.GR

[link]
This summary builds substantially on my summary of NERFs, so if you haven't yet read that, I recommend doing so first! The idea of a NERF is learn a neural network that represents a 3D scene, and from which you can, once the model is trained, sample an image of that scene from any desired angle. This involves structuring your neural network as a function that predicts the RGB color and density/opacity for a given point in 3D space (x, y, z), from a given viewing angle (theta, phi). With such a function, you can generate predictions of what images taken from certain angles would look like by sampling along a viewing ray, and integrating the combined hue and opacity into an aggregated view. This prediction can then be compared to a true image taken from that direction, and gradients passed backwards into the prediction model. An important assumption of this model is that the scene being photographed is static; specifically, that every point in space is always inhabited by the same part of the 3D object, regardless of what angle it's viewed from. This is a reasonable assumption for photos of inanimate objects, or of humans in highly controlled lab settings, but it is often not true for humans when you, say, ask them to take a selfie video of themselves. Even if they're trying to keep roughly still, there will be slight shifts in the location and position of their head between frames, and the authors of this paper show that this can lead to strange artifacts if you naively try to train a NERF from the images (including a particularly odd one where it hallucinates tiny copies of the image in the air surrounding the face). https://i.imgur.com/IUVh6uM.png The fix proposed by this paper is to apply a learnable deformation field to each image, where the notion is to deform each view into being in one canonical position (fixed per network, since, again, one network corresponds to a single scene). This means that, along with learning the parameters of the NERF itself, you're also learning what deformation to apply to each training image to get it into this canonical position. This is done by parametrizing the deformation in a particular way, and then having that deformation be conditioned by a latent vector that's trained similar to how you'd train an embedding (one learned vector per image example). The parametrization of the deformation is honestly a little bit over my head, given my lack of grounding in 3D modeling, but my general sense is that it applies some constraints and regularization to ensure that the learned deformations are realistic, insofar as humans are mostly rigid (one patch of skin on my forehead generally doesn't move except in concordance with the rest of my forehead), but with some possibility for elasticity (skin can stretch if I, say, smile). The authors also include an annealing scheme whereby, early in training, the model focuses on learning course (large-scale) deformations, and later in training, it's allowed to also learn weights for more precise deformations. This is to hopefully match macro-scale shifts before adding the noise of precise changes. This addition of a learned deformation is most of the contribution of this method: with it applied, they show that they're able to learn realistic NERFs from selfies, which they term "NERFIES". They mention a few pieces of concurrent work that try to solve the same problem of non-static human subjects in different ways, but I haven't had a chance to read those, so I can't really comment on how NERFIES stacks up to alternate approaches, but it appears to be as least one empirically convincing solution to the problem it's aiming at. |

About