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.

Deep Residual Learning for Image Recognition

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

arXiv e-Print archive - 2015 via Local Bibsonomy

Keywords: dblp

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

arXiv e-Print archive - 2015 via Local Bibsonomy

Keywords: dblp

[link]
Deeper networks should never have a higher **training** error than smaller ones. In the worst case, the layers should "simply" learn identities. It seems as this is not so easy with conventional networks, as they get much worse with more layers. So the idea is to add identity functions which skip some layers. The network only has to learn the **residuals**. Advantages: * Learning the identity becomes learning 0 which is simpler * Loss in information flow in the forward pass is not a problem anymore * No vanishing / exploding gradient * Identities don't have parameters to be learned ## Evaluation The learning rate starts at 0.1 and is divided by 10 when the error plateaus. Weight decay of 0.0001 ($10^{-4}$), momentum of 0.9. They use mini-batches of size 128. * ImageNet ILSVRC 2015: 3.57% (ensemble) * CIFAR-10: 6.43% * MS COCO: 59.0% mAp@0.5 (ensemble) * PASCAL VOC 2007: 85.6% mAp@0.5 * PASCAL VOC 2012: 83.8% mAp@0.5 ## See also * [DenseNets](http://www.shortscience.org/paper?bibtexKey=journals/corr/1608.06993) |

Online Continual Learning with Maximally Interfered Retrieval

Rahaf Aljundi and Lucas Caccia and Eugene Belilovsky and Massimo Caccia and Laurent Charlin and Tinne Tuytelaars

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, stat.ML

**First published:** 2019/08/11 (3 years ago)

**Abstract:** Continual learning, the setting where a learning agent is faced with a never
ending stream of data, continues to be a great challenge for modern machine
learning systems. In particular the online or "single-pass through the data"
setting has gained attention recently as a natural setting that is difficult to
tackle. Methods based on replay, either generative or from a stored memory,
have been shown to be effective approaches for continual learning, matching or
exceeding the state of the art in a number of standard benchmarks. These
approaches typically rely on randomly selecting samples from the replay memory
or from a generative model, which is suboptimal. In this work we consider a
controlled sampling of memories for replay. We retrieve the samples which are
most interfered, i.e. whose prediction will be most negatively impacted by the
foreseen parameters update. We show a formulation for this sampling criterion
in both the generative replay and the experience replay setting, producing
consistent gains in performance and greatly reduced forgetting.
more
less

Rahaf Aljundi and Lucas Caccia and Eugene Belilovsky and Massimo Caccia and Laurent Charlin and Tinne Tuytelaars

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, stat.ML

[link]
Disclaimer: I am an author # Intro Experience replay (ER) and generative replay (GEN) are two effective continual learning strategies. In the former, samples from a stored memory are replayed to the continual learner to reduce forgetting. In the latter, old data is compressed with a generative model and generated data is replayed to the continual learner. Both of these strategies assume a random sampling of the memories. But learning a new task doesn't cause **equal** interference (forgetting) on the previous tasks! In this work, we propose a controlled sampling of the replays. Specifically, we retrieve the samples which are most interfered, i.e. whose prediction will be most negatively impacted by the foreseen parameters update. The method is called Maximally Interfered Retrieval (MIR). ## Cartoon for explanation https://i.imgur.com/5F3jT36.png Learning about dogs and horses might cause more interference on lions and zebras than on cars and oranges. Thus, replaying lions and zebras would be a more efficient strategy. # Method 1) incoming data: $(X_t,Y_t)$ 2) foreseen parameter update: $\theta^v= \theta-\alpha\nabla\mathcal{L}(f_\theta(X_t),Y_t)$ ### applied to ER (ER-MIR) 3) Search for the top-$k$ values $x$ in the stored memories using the criterion $$s_{MI}(x) = \mathcal{L}(f_{\theta^v}(x),y) -\mathcal{L}(f_{\theta}(x),y)$$ ### or applied to GEN (GEN-MIR) 3) $$ \underset{Z}{\max} \, \mathcal{L}\big(f_{\theta^v}(g_\gamma(Z)),Y^*\big) -\mathcal{L}\big(f_{\theta}(g_\gamma(Z)),Y^*\big) $$ $$ \text{s.t.} \quad ||z_i-z_j||_2^2 > \epsilon \forall z_i,z_j \in Z \,\text{with} \, z_i\neq z_j $$ i.e. search in the latent space of a generative model $g_\gamma$ for samples that are the most forgotten given the foreseen update. 4) Then add theses memories to incoming data $X_t$ and train $f_\theta$ # Results ### qualitative https://i.imgur.com/ZRNTWXe.png Whilst learning 8s and 9s (first row), GEN-MIR mainly retrieves 3s and 4s (bottom two rows) which are similar to 8s and 9s respectively. ### quantitative GEN-MIR was tested on MNIST SPLIT and Permuted MNIST, outperforming the baselines in both cases. ER-MIR was tested on MNIST SPLIT, Permuted MNIST and Split CIFAR-10, outperforming the baselines in all cases. # Other stuff ### (for avid readers) We propose a hybrid method (AE-MIR) in which the generative model is replaced with an autoencoder to facilitate the compression of harder dataset like e.g. CIFAR-10. |

LSTM: A Search Space Odyssey

Greff, Klaus and Srivastava, Rupesh Kumar and Koutník, Jan and Steunebrink, Bas R. and Schmidhuber, Jürgen

arXiv e-Print archive - 2015 via Local Bibsonomy

Keywords: dblp

Greff, Klaus and Srivastava, Rupesh Kumar and Koutník, Jan and Steunebrink, Bas R. and Schmidhuber, Jürgen

arXiv e-Print archive - 2015 via Local Bibsonomy

Keywords: dblp

[link]
This paper presents an extensive evaluation of variants of LSTM networks. Specifically, they start from what they consider to be the vanilla architecture and, from it, also consider 8 variants which correspond to small modifications on the vanilla case. The vanilla architecture is the one described in Graves & Schmidhuber (2005) \cite{journals/nn/GravesS05}, and the variants consider removing single parts of it (input,forget,output gates or activation functions), coupling the input and forget gate (which is inspired from GRU) or having full recurrence between all gates (which comes from the original LSTM formulation). In their experimental setup, they consider 3 datasets: TIMIT (speech recognition), IAM Online Handwriting Database (character recognition) and JSB Chorales (polyphonic music modeling). For each, they tune the hyper-parameters of each of the 9 architectures, using random search based on 200 samples. Then, they keep the 20 best hyper-parameters and use the statistics of those as a basis for comparing the architectures. #### My two cents This was a very useful ready. I'd make it a required read for anyone that wants to start using LSTMs. First, I found the initial historical description of the developments surrounding LSTMs very interesting and clarifying. But more importantly, it presents a really useful picture of LSTMs that can both serve as a good basis for starting to use LSTMs and also an insightful (backed with data) exposition of the importance of each part in the LSTM. The analysis based on an fANOVA (which I didn't know about until now) is quite neat. Perhaps the most surprising observation is that momentum actually doesn't seem to help that much. Investigating second order interaction between hyper-parameters was a smart thing to do (showing that tuning the learning rate and hidden layer jointly might not be that important, which is a useful insight).The illustrations in Figure 4, layout out the estimated relationship (with uncertainty) between learning rate / hidden layer size / input noise variance and performance / training time is also full of useful information. I wont repeat here the main observations of the paper, which are laid out clearly in the conclusion (section 6). Additionally, my personal take-away point is that, in an LSTM implementation, it might still be useful to support the removal peepholes or having coupled input and forget gates, since they both yielded the ultimate best test set performance on at least one of the datasets (I'm assuming it was also best on the validation set, though this might not be the case...) The fANOVE analysis makes it clear that the learning rate is the most critical hyper-parameter to tune (can be "make or break"). That said, this is already well known. And the fact that it explains so much of the variance might reflect a bias of the analysis towards a situation where the learning rate isn't tuned as well as it could be in practice (this is afterall THE hyper-parameter that neural net researcher spend the most time tuning in practice). So, as future work, this suggests perhaps doing another round of the same analysis (which is otherwise really neatly setup), where more effort is always put on tuning the learning rate, individually for each of the other hyper-parameters. In other words, we'd try to ignore the regions of hyper-parameter space that correspond to bad learning rates, in order to "marginalize out" its effect. This would thus explore the perhaps more realistic setup that assumes one always tunes the learning rate as best as possible. Also, considering a less aggressive gradient clipping into the hyper-parameter search would be interesting since, as the authors admit, clipping within [-1,1] might have been too much and could explain why it didn't help Otherwise, a really great and useful read! |

Better-than-Demonstrator Imitation Learning via Automatically-Ranked Demonstrations

Daniel S. Brown and Wonjoon Goo and Scott Niekum

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, stat.ML

**First published:** 2019/07/09 (3 years ago)

**Abstract:** The performance of imitation learning is typically upper-bounded by the
performance of the demonstrator. While recent empirical results demonstrate
that ranked demonstrations allow for better-than-demonstrator performance,
preferences over demonstrations may be difficult to obtain, and little is known
theoretically about when such methods can be expected to successfully
extrapolate beyond the performance of the demonstrator. To address these
issues, we first contribute a sufficient condition for better-than-demonstrator
imitation learning and provide theoretical results showing why preferences over
demonstrations can better reduce reward function ambiguity when performing
inverse reinforcement learning. Building on this theory, we introduce
Disturbance-based Reward Extrapolation (D-REX), a ranking-based imitation
learning method that injects noise into a policy learned through behavioral
cloning to automatically generate ranked demonstrations. These ranked
demonstrations are used to efficiently learn a reward function that can then be
optimized using reinforcement learning. We empirically validate our approach on
simulated robot and Atari imitation learning benchmarks and show that D-REX
outperforms standard imitation learning approaches and can significantly
surpass the performance of the demonstrator. D-REX is the first imitation
learning approach to achieve significant extrapolation beyond the
demonstrator's performance without additional side-information or supervision,
such as rewards or human preferences. By generating rankings automatically, we
show that preference-based inverse reinforcement learning can be applied in
traditional imitation learning settings where only unlabeled demonstrations are
available.
more
less

Daniel S. Brown and Wonjoon Goo and Scott Niekum

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, stat.ML

[link]
## General Framework Extends T-REX (see [summary](https://www.shortscience.org/paper?bibtexKey=journals/corr/1904.06387&a=muntermulehitch)) so that preferences (rankings) over demonstrations are generated automatically (back to the common IL/IRL setting where we only have access to a set of unlabeled demonstrations). Also derives some theoretical requirements and guarantees for better-than-demonstrator performance. ## Motivations * Preferences over demonstrations may be difficult to obtain in practice. * There is no theoretical understanding of the requirements that lead to outperforming demonstrator. ## Contributions * Theoretical results (with linear reward function) on when better-than-demonstrator performance is possible: 1- the demonstrator must be suboptimal (room for improvement, obviously), 2- the learned reward must be close enough to the reward that the demonstrator is suboptimally optimizing for (be able to accurately capture the intent of the demonstrator), 3- the learned policy (optimal wrt the learned reward) must be close enough to the optimal policy (wrt to the ground truth reward). Obviously if we have 2- and a good enough RL algorithm we should have 3-, so it might be interesting to see if one can derive a requirement from only 1- and 2- (and possibly a good enough RL algo). * Theoretical results (with linear reward function) showing that pairwise preferences over demonstrations reduce the error and ambiguity of the reward learning. They show that without rankings two policies might have equal performance under a learned reward (that makes expert's demonstrations optimal) but very different performance under the true reward (that makes the expert optimal everywhere). Indeed, the expert's demonstration may reveal very little information about the reward of (suboptimal or not) unseen regions which may hurt very much the generalizations (even with RL as it would try to generalize to new states under a totally wrong reward). They also show that pairwise preferences over trajectories effectively give half-space constraints on the feasible reward function domain and thus may decrease exponentially the reward function ambiguity. * Propose a practical way to generate as many ranked demos as desired. ## Additional Assumption Very mild, assumes that a Behavioral Cloning (BC) policy trained on the provided demonstrations is better than a uniform random policy. ## Disturbance-based Reward Extrapolation (D-REX) ![](https://i.imgur.com/9g6tOrF.png) ![](https://i.imgur.com/zSRlDcr.png) They also show that the more noise added to the BC policy the lower the performance of the generated trajs. ## Results Pretty much like T-REX. |

The Lottery Ticket Hypothesis for Pre-trained BERT Networks

Chen, Tianlong and Frankle, Jonathan and Chang, Shiyu and Liu, Sijia and Zhang, Yang and Wang, Zhangyang and Carbin, Michael

arXiv e-Print archive - 2020 via Local Bibsonomy

Keywords: dblp

Chen, Tianlong and Frankle, Jonathan and Chang, Shiyu and Liu, Sijia and Zhang, Yang and Wang, Zhangyang and Carbin, Michael

arXiv e-Print archive - 2020 via Local Bibsonomy

Keywords: dblp

[link]
This is an interesting paper, investigating (with a team that includes the original authors of the Lottery Ticket paper) whether the initializations that result from BERT pretraining have Lottery Ticket-esque properties with respect to their role as initializations for downstream transfer tasks. As background context, the Lottery Ticket Hypothesis came out of an observation that trained networks could be pruned to remove low-magnitude weights (according to a particular iterative pruning strategy that is a bit more complex than just "prune everything at the end of training"), down to high levels of sparsity (5-40% of original weights, and that those pruned networks not only perform well at the end of training, but also can be "rewound" back to their initialization values (or, in some cases, values from early in training) and retrained in isolation, with the weights you pruned out of the trained network still set to 0, to a comparable level of accuracy. This is thought of as a "winning ticket" because the hypothesis Frankle and Carbin generated is that the reason we benefit from massively overparametrized neural networks is that we are essentially sampling a large number of small subnetworks within the larger ones, and that the more samples we get, the likelier it is we find a "winning ticket" that starts our optimization in a place conducive to further training. In this particular work, the authors investigate a slightly odd variant of the LTH. Instead of looking at training runs that start from random initializations, they look at transfer tasks that start their learning from a massively-pretrained BERT language model. They try to find out: 1) Whether you can find "winning tickets" as subsets of the BERT initialization for a given downstream task 2) Whether those winning tickets generalize, i.e. whether a ticket/pruning mask for one downstream task can also have high performance on another. If that were the case, it would indicate that much of the value of a BERT initialization for transfer tasks could be captured by transferring only a small percentage of BERT's (many) weights, which would be beneficial for compression and mobile applications An interesting wrinkle in the LTH literature is the question of whether true "winning tickets" can be found (in the sense of the network being able to retrain purely from the masked random initializations), or whether it can only retrain to a comparable accuracy by rewinding to an early stage in training, but not the absolute beginning of training. Historically, the former has been difficult and sometimes not possible to find in more complex tasks and networks. https://i.imgur.com/pAF08H3.png One finding of this paper is that, when your starting point is BERT initialization, you can indeed find "winning tickets" in the first sense of being able to rewind the full way back to the beginning of (downstream task) training, and retrain from there. (You can see this above with the results for IMP, Iterative Magnitude Pruning, rolling back to theta-0). This is a bit of an odd finding to parse, since it's not like BERT really is a random initialization itself, but it does suggest that part of the value of BERT is that it contains subnetworks that, from the start of training, are in notional optimization basins that facilitate future training. A negative result in this paper is that, by and large, winning tickets on downstream tasks don't transfer from one to another, and, to the extent that they do transfer, it mostly seems to be according to which tasks had more training samples used in the downstream mask-finding process, rather than any qualitative properties of the task. The one exception to this was if you did further training of the original BERT objective, Masked Language Modeling, as a "downstream task", and took the winning ticket mask from that training, which then transferred to other tasks. This is some validation of the premise that MLM is an unusually good training task in terms of its transfer properties. An important thing to note here is that, even though this hypothesis is intriguing, it's currently quite computationally expensive to find "winning tickets", requiring an iterative pruning and retraining process that takes far longer than an original training run would have. The real goal here, which this is another small step in the hopeful direction of, is being able to analytically specify subnetworks with valuable optimization properties, without having to learn them from data each time (which somewhat defeats the point, if they're only applicable for the task they're trained on, though is potentially useful is they do transfer to some other tasks, as has been shown within a set of image-prediction tasks). |

About