A common critique of deep learning is its brittleness off-distribution, combined with its tendency to give confident predictions for off-distribution inputs, as is seen in the case of adversarial examples. In response to this critique, a number of different methods have cropped up in recent years, that try to capture a model's uncertainty as well as its overall prediction. This paper tries to do a broad evaluation of uncertainty methods, and, particularly, to test how they perform on out of distribution data, including both data that is perturbed from its original values, and fully OOD data from ground-truth categories never seen during training. Ideally, we would want an uncertainty method that is less confident in its predictions as data is made more dissimilar from the distribution that the model is trained on. Some metrics the paper uses for capturing this are: 

- Brier Score (The difference between predicted score and ground truth 0/1 label, averaged over all examples)
- Negative Log Likelihood
- Expected Calibration Error (Within a given bucket, this is calculated as the difference between accuracy to ground truth labels, and the average predicted score in that bucket, capturing that you'd ideally want to have a lower predicted score in cases where you have low accuracy, and vice versa)
- Entropy - For labels that are fully out of distribution, and don't map to any of the model's categories, you can't directly calculate ground truth accuracy, but you can ideally ask for a model that has high entropy (close to uniform) probabilities over the classes it knows about when the image is drawn from an entirely different class

The authors test over image datasets small (MNIST) and large (ImageNet and CIFAR10), as well as a categorical ad-click-prediction dataset. They came up with some interesting findings. 

https://i.imgur.com/EVnjS1R.png

1. More fully principled Bayesian estimation of posteriors over parameters, in the form of Stochastic Variational Inference, works well on MNIST, but quite poorly on either categorical data or higher dimensional image datasets 

https://i.imgur.com/3emTYNP.png

2. Temperature scaling, which basically performs a second supervised calibration using a hold-out set to push your probabilities towards true probabilities, performs well in-distribution but collapses fairly quickly off-distribution (which sort of makes sense given that it too is just another supervised method that can do poorly when off-distribution) 
3. In general, ensemble methods, where you train different models on different subsets of the data and take their variance as uncertainty, perform the best across the bigger image models as well as the ad click model, likely because SVI (along with many other Bayesian methods) is too computationally intensive to get to work well on higher-dimensional data 
4. Overall, none of the methods worked particularly well, and even the best-performing ones were often confidently wrong off-distribution 

I think it's fair to say that we're far from where we wish we were when it comes to models that "know when they don't know," and this paper does a good job of highlighting that in specific fashion.

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.

The [paper](https://homes.cs.washington.edu/~pedrod/papers/cacm12.pdf) presents some key lessons and "folk wisdom" that machine learning researchers and practitioners have learnt from experience and which are hard to find in textbooks.

### 1. Learning = Representation + Evaluation + Optimization

All machine learning algorithms have three components:
*    **Representation** for a  learner is the set if classifiers/functions that can be possibly learnt. This set is called *hypothesis space*. If a function is not in hypothesis space, it can not be learnt.
*    **Evaluation** function tells how good the machine learning model is.
*    **Optimisation** is the method to search for the most optimal learning model.

### 2. Its Generalization That Counts

The fundamental goal of machine learning is to generalize beyond the training set. The data used to evaluate the model must be kept separate from the data used to learn the model. When we use generalization as a goal, we do not have access to a function that we can optimize. So we have to use training error as a proxy for test error.

### 3. Data Alone Is Not Enough

Since our ultimate goal is generalization (see point 2), there is no such thing as **"enough"**  data. Some knowledge beyond the data is needed to generalize beyond the data. Another way to put is "No learner can beat random guessing over all possible functions." But instead of hard-coding assumptions, learners should allow assumptions to be explicitly stated, varied and incorporated automatically into the model.

### 4. Overfitting Has Many Faces

One way to interpret overfitting is to break down generalization error into two components: bias and variance. **Bias** is the tendency of the learner to constantly learn the same wrong thing (in the image, a high bias would mean more distance from the centre). **Variance** is the tendency to learn random things irrespective of the signal (in the image, a high variance would mean more scattered points). 

![Bias Variance Diagram](https://dl.dropboxusercontent.com/u/56860240/A-Paper-A-Week/BiasVarianceDiagram.png)

A more powerful learner (one that can learn many models) need not be better than a less powerful one as they can have a high variance.  While noise is not the only reason for overfitting, it can indeed aggravate the problem. Some tools against overfitting are - **cross-validation**, **regularization**, **statistical significance testing**, etc. 

### 5. Intuition Fails In High Dimensions

Generalizing correctly becomes exponentially harder as dimensionality (number of features) become large. Machine learning algorithms depend on similarity-based reasoning which breaks down in high dimensions as a fixed-size training set covers only a small fraction of the large input space. Moreover, our intuitions from three-dimensional space often do not apply to higher dimensional spaces. So the **curse of dimensionality** may outweigh the benefits of having more features. Though, in most cases, learners benefit from the **blessing of non-uniformity** as data points are concentrated in lower-dimensional manifolds. Learners can implicitly take advantage of this lower effective dimension or use dimensionality reduction techniques.

### 6. Theoretical Guarantees Are Not What They Seem  

A common type of bound common when dealing with machine learning algorithms is related to the number of samples needed to ensure good generalization. But these bounds are very loose in nature. Moreover, the bound says that given a large enough training dataset, our learner would return a good hypothesis with high probability or would not find a consistent hypothesis. It does not tell us anything about how to select a good hypothesis space.

Another common type of bound is the asymptotic bound which says "given infinite data, the learner is guaranteed to output correct classifier". But in practice we never have infinite data and data alone is not enough (see point 3). So theoretical guarantees should be used to understand and drive the algorithm design and not as the only criteria to select algorithm.

### 7. Feature Engineering Is The Key

Machine Learning is an iterative process where we train the learner, analyze the results, modify the learner/data and repeat. Feature engineering is a crucial step in this pipeline. Having the right kind of features (independent features that correlate well with the class) makes learning easier. But feature engineering is also difficult because it requires domain specific knowledge which extends beyond just the data at hand (see point 3).

### 8. More Data Beats A Clever Algorithm

As a rule of thumb, a dumb algorithm with lots of data beats a clever algorithm with a modest amount of data. But more data means more scalability issues. Fixed size learners (parametric learners) can take advantage of data only to an extent beyond which adding more data does not improve the results. Variable size learners (non-parametric learners) can, in theory, learn any function given sufficient amount of data. Of course, even non-parametric learners are bound by limitations of memory and computational power. 

    
### 9. Learn Many Models, Not Just One

In early days of machine learning, the model/learner to be trained was pre-determined and the focus was on tuning it for optimal performance. Then the focus shifted to trying many variants of different learners. Now the focus is on combining the various variants of different algorithms to generate the most optimal results. Such model ensembling techniques include *bagging*, *boosting* and *stacking*.

### 10. Simplicity Does Not Imply Accuracy

Though Occam's razor suggests that machine learning models should be kept simple, there is no necessary connection between the number of parameters of a model and its tendency to overfit. The complexity of a model can be related to the size of hypothesis space as smaller spaces allow the hypothesis to be generated by smaller, simpler codes. But there is another side to this picture - A learner with a larger hypothesis space that tries fewer hypotheses is less likely to overfit than one that tries more hypotheses from a smaller space. So hypothesis space size is just a rough guide towards accuracy. Domingos conclude in his [other paper](http://homes.cs.washington.edu/~pedrod/papers/dmkd99.pdf) that "simpler hypotheses should be preferred because simplicity is a virtue in its own right, not because of a hypothetical connection with accuracy."


### 11. Representation Does Not Imply Learnable

Just because a function can be represented, does not mean that the function can actually be learnt. Restrictions imposed by data, time and memory, limit the functions that can actually be learnt in a feasible manner. For example, decision tree learners can not learn trees with more leaves than the number of training data points. The right question to ask is "whether  a function can be learnt" and not "whether a function can be represented". 

### 12. Correlation Does Not Imply Causation

Correlation may hint towards a possible cause and effect relationship but that needs to be investigated and validated. On the face of it, correlation can not be taken as proof of causation.

This paper proposes a variant of Neural Turing Machine (NTM) for meta-learning or "learning to learn", in the specific context of few-shot learning (i.e. learning from few examples). Specifically, the proposed model is trained to ingest as input a training set of examples and improve its output predictions as examples are processed, in a purely feed-forward way. This is a form of meta-learning because the model is trained so that its forward pass effectively executes a form of "learning" from the examples it is fed as input.

During training, the model is fed multiples sequences (referred to as episodes) of labeled examples $({\bf x}_1, {\rm null}), ({\bf x}_2, y_1), \dots, ({\bf x}_T, y_{T-1})$, where $T$ is the size of the episode. For instance, if the model is trained to learn how to do 5-class classification from 10 examples per class, $T$ would be $5 \times 10 = 50$. Mainly, the paper presents experiments on the Omniglot dataset, which has 1623 classes. In these experiments, classes are separated into 1200 "training classes" and 423 "test classes", and each episode is generated by randomly selecting 5 classes (each assigned some arbitrary vector representation, e.g. a  one-hot vector that is consistent within the episode, but not across episodes) and constructing a randomly ordered sequence of 50 examples from within the chosen 5 classes. Moreover, the correct label $y_t$ of a given input ${\bf x}_t$ is always provided only at the next time step, but the model is trained to be good at its prediction of the label of ${\bf x}_t$ at the current time step. This is akin to the scenario of online learning on a stream of examples, where the label of an example is revealed only once the model has made a prediction.

The proposed NTM is different from the original NTM of Alex Graves, mostly in how it writes into its memory. The authors propose to focus writing to either the least recently used memory location or the most recently used memory location. Moreover, the least recently used memory location is reset to zero before every write (an operation that seems to be ignored when backpropagating gradients).

Intuitively, the proposed NTM should learn a strategy by which, given a new input, it looks into its memory for information from other examples earlier in the episode (perhaps similarly to what a nearest neighbor classifier would do) to predict the class of the new input.

The paper presents experiments in learning to do multiclass classification on the Omniglot dataset and regression based on functions synthetically generated by a GP. The highlights are that:

1. The proposed model performs much better than an LSTM and better than an NTM with the original write mechanism of Alex Graves (for classification).
2. The proposed model even performs better than a 1st nearest neighbor classifier.
3. The proposed model is even shown to outperform human performance, for the 5-class scenario.
4. The proposed model has decent performance on the regression task, compared to GP predictions using the groundtruth kernel.

**My two cents**

This is probably one of my favorite ICML 2016 papers. I really think meta-learning is a problem that deserves more attention, and this paper presents both an interesting proposal for how to do it and an interesting empirical investigation of it. 

Much like previous work [\[1\]][1] [\[2\]][2], learning is based on automatically generating a meta-learning training set. This is clever I think, since a very large number of such "meta-learning" examples (the episodes) can be constructed, thus transforming what is normally a "small data problem" (few shot learning) into a "big data problem", for which deep learning is more effective.

I'm particularly impressed by how the proposed model outperforms a 1-nearest neighbor classifier. That said, the proposed NTM actually performs 4 reads at each time step, which suggests that a fairer comparison might be with a 4-nearest neighbor classifier. I do wonder how this baseline would compare.

I'm also impressed with the observation that the proposed model surpassed humans.

The paper also proposes to use 5-letter words to describe classes, instead of one-hot vectors. The motivation is that this should make it easier for the model to scale to much more than 5 classes. However, I don't entirely follow the logic as to why one-hot vectors are problematic. In fact, I would think that arbitrarily assigning 5-letter words to classes would instead imply some similarity between classes that share letters that is arbitrary and doesn't reflect true class similarity. 

Also, while I find it encouraging that the performance for regression of the proposed model is decent, I'm curious about how it would compare with a GP approach that incrementally learns the kernel's hyper-parameter (instead of using the groundtruth values, which makes this baseline unrealistically strong).

Finally, I'm still not 100% sure how exactly the NTM is able to implement the type of feed-forward inference I'd expect to be required. I would expect it to learn a memory representation of examples that combines information from the input vector ${\bf x}_t$ *and* its label $y_t$. However, since the label of an input is presented at the following time step in an episode, it is not intuitive to me then how the read/write mechanisms are able to deal with this misalignment. My only guess is that since the controller is an LSTM, then it can somehow remember ${\bf x}_t$ until it gets $y_t$ and appropriately include the combined information into the memory. This could be supported by the fact that using a non-recurrent feed-forward controller is much worse than using an LSTM controller. But I'm not 100% sure of this either.

All the above being said, this is still a really great paper, which I hope will help stimulate more research on meta-learning. Hopefully code for this paper can eventually be released, which would help in popularizing the topic.

[1]: http://snowedin.net/tmp/Hochreiter2001.pdf
[2]: http://www.thespermwhale.com/jaseweston/ram/papers/paper_16.pdf

Ongoing declines in production of the world's fisheries may have serious ecological and socioeconomic consequences. As a result, a number of international efforts have sought to improve management and prevent overexploitation, while helping to maintain biodiversity and a sustainable food supply. Although these initiatives have received broad acceptance, the extent to which corrective measures have been implemented and are effective remains largely unknown. We used a survey approach, validated with empirical data, and enquiries to over 13,000 fisheries experts (of which 1,188 responded) to assess the current effectiveness of fisheries management regimes worldwide; for each of those regimes, we also calculated the probable sustainability of reported catches to determine how management affects fisheries sustainability. Our survey shows that 7% of all coastal states undergo rigorous scientific assessment for the generation of management policies, 1.4% also have a participatory and transparent processes to convert scientific recommendations into policy, and 0.95% also provide for robust mechanisms to ensure the compliance with regulations; none is also free of the effects of excess fishing capacity, subsidies, or access to foreign fishing. A comparison of fisheries management attributes with the sustainability of reported fisheries catches indicated that the conversion of scientific advice into policy, through a participatory and transparent process, is at the core of achieving fisheries sustainability, regardless of other attributes of the fisheries. Our results illustrate the great vulnerability of the world's fisheries and the urgent need to meet well-identified guidelines for sustainable management; they also provide a baseline against which future changes can be quantified. Author Summary Top Global fisheries are in crisis: marine fisheries provide 15% of the animal protein consumed by humans, yet 80% of the world's fish stocks are either fully exploited, overexploited or have collapsed. Several international initiatives have sought to improve the management of marine fisheries, hoping to reduce the deleterious ecological and socioeconomic consequence of the crisis. Unfortunately, the extent to which countries are improving their management and whether such intervention ensures the sustainability of the fisheries remain unknown. Here, we surveyed 1,188 fisheries experts from every coastal country in the world for information about the effectiveness with which fisheries are being managed, and related those results to an index of the probable sustainability of reported catches. We show that the management of fisheries worldwide is lagging far behind international guidelines recommended to minimize the effects of overexploitation. Only a handful of countries have a robust scientific basis for management recommendations, and transparent and participatory processes to convert those recommendations into policy while also ensuring compliance with regulations. Our study also shows that the conversion of scientific advice into policy, through a participatory and transparent process, is at the core of achieving fisheries sustainability, regardless of other attributes of the fisheries. These results illustrate the benefits of participatory, transparent, and science-based management while highlighting the great vulnerability of the world's fisheries services. The data for each country can be viewed at http://as01.ucis.dal.ca/ramweb/surveys/fishery_assessment .