**Stochastic Cubic Regularization**

This paper proposes a stochastic variant of a classic algorithm—the cubic-regularized Newton method [Nesterov and Polyak 2006]. The proposed algorithm efficiently escapes saddle points and finds approximate local minima for general smooth, nonconvex functions in only $\mathcal{\tilde{O}}(\epsilon^{-3.5})$ stochastic gradient and stochastic Hessian-vector product evaluations. The latter can be computed as efficiently as stochastic gradients. This improves upon the $\mathcal{\tilde{O}}(\epsilon^{-4})$ rate of stochastic gradient descent. Our rate matches the best-known result for finding local minima without requiring any delicate acceleration or variance-reduction techniques. … **k-mer**

The term k-mer typically refers to all the possible substrings, of length k, that are contained in a string. In Computational genomics, k-mers refer to all the possible subsequences (of length k) from a read obtained through DNA Sequencing. The amount of k-mers possible given a string of length, L, is L-k+1 whilst the number of possible k-mers given n possibilities (4 in the case of DNA e.g. ACTG) is n^{k}. K-mers are typically used during Sequence assembly, but can also be used in Sequence alignment.

➘ “n-gram” … **DisentAngled Representation Learning Agent (DARLA)**

Domain adaptation is an important open problem in deep reinforcement learning (RL). In many scenarios of interest data is hard to obtain, so agents may learn a source policy in a setting where data is readily available, with the hope that it generalises well to the target domain. We propose a new multi-stage RL agent, DARLA (DisentAngled Representation Learning Agent), which learns to see before learning to act. DARLA’s vision is based on learning a disentangled representation of the observed environment. Once DARLA can see, it is able to acquire source policies that are robust to many domain shifts – even with no access to the target domain. DARLA significantly outperforms conventional baselines in zero-shot domain adaptation scenarios, an effect that holds across a variety of RL environments (Jaco arm, DeepMind Lab) and base RL algorithms (DQN, A3C and EC). …

# If you did not already know

**09**
*Friday*
Mar 2018

Posted What is ...

in
Advertisements