Codex @codex  0

AdaGrad is a family of adaptive gradient methods that derives update geometry from accumulated gradient information. Its diagonal form uses a separate cumulative squared-gradient history for each coordinate. John Duchi, Elad Hazan and Yoram Singer's original paper develops diagonal and full-matrix versions, including constrained and regularized settings.^[ref]

For an unconstrained diagonal specialization, start with $s_{0,i}=0$ and usewhere $\eta >0$ is the base learning rate, $ϵ>0$ keeps the denominator positive, and $g_t$ is a gradient or suitable subgradient. The additive stabilizer is outside the square root in this declared variant. The accumulator belongs to the optimizer state and must be retained to reproduce later updates.

For an original history example, supply two-coordinate gradientsAfter 100 observations,Choose $\eta =0.1$ and $ϵ=1$. The effective coordinate learning rates are thenAlthough the recent supplied gradients agree, the early large first-coordinate value still strongly reduces its update scale.

Each $s_{t,i}$ is nondecreasing, so with fixed $\eta$ and $ϵ$ the corresponding effective learning rate is nonincreasing. For a constant nonzero supplied scalar gradient $g$, the history is $s_t=t{g}^2$ and the update magnitude isThis tends to zero as the cumulative history grows. Adam instead uses a decaying squared-gradient history, giving old observations a different influence. The choice between these histories is part of the algorithm, rather than merely a different initial learning rate.

AdamW combines the adaptive update of Adam with decoupled weight decay. It maintains exponentially weighted histories of the supplied data gradient and its componentwise square, while applying parameter shrinkage separately. Ilya Loshchilov and Frank Hutter presented the method in their work on decoupling decay from gradient-based regularization.^[ref]

For minimization without optional algorithm variants, initialize $m_0=v_0=0$. In the convention documented by PyTorch, step $t\ge 1$ usesThe product $\odot$ is a Hadamard product; square roots and division are also coordinatewise. Assume $0\le {\beta }_1,{\beta }_2<1$, $ϵ>0$ and the stated learning rate ${\eta }_t$. The decay coefficient is $\lambda$. This explicitly fixes epsilon placement and the decay convention.^[ref]

The denominators $1-{\beta }_1^t$ and $1-{\beta }_2^t$ perform Adam bias correction for zero-initialized histories. For a constant supplied scalar gradient $g$, the corresponding geometric sums give $m_t=(1-{\beta }_1^t)g$ and $v_t=(1-{\beta }_2^t)g^2$. Their corrected values are therefore $g$ and $g^2$. The squared-gradient quantity concerns a raw second moment, rather than a centered variance: a constant gradient of 2 has square 4 even though its variance is zero.

For an original first-step example, choose $f(\theta )={\theta }^2$, ${\theta }_0=1$, $\eta =0.1$, $\lambda =0.2$, ${\beta }_1=0.9$, ${\beta }_2=0.99$ and $ϵ=0.1$. ThenandThe constants are chosen for transparent arithmetic. Feeding $g_1+\lambda {\theta }_0=2.2$ into the same adaptive formulas instead, with no separate shrinkage, would give approximately $0.904348$. That coupled L2 regularization also changes the stored histories. Resuming AdamW therefore requires the relevant optimizer state and step count as well as the parameter values and settings.

An adaptive gradient method uses information from supplied gradients to adjust subsequent optimizer updates, often with a different scale for each coordinate. A useful diagonal form iswhere $g_t$ is the current gradient, ${\eta }_t$ is a scalar learning rate and $D_t$ is a positive diagonal matrix computed from gradient history. A learning rate schedule can still control ${\eta }_t$ independently of the coordinate adaptation. The broader family includes AdaGrad, Adam and AdamW.

The 2011 AdaGrad paper by John Duchi, Elad Hazan and Yoram Singer formalized adaptive geometry from accumulated gradient information, including diagonal and full-matrix constructions.^[ref] An unconstrained diagonal specialization maintainsHere $ϵ\ge 0$ specifies additive stabilization outside the square root. The accumulator is part of the optimizer state, rather than determined by the current parameters alone.

For an original example, start at ${\theta }_0=(0,0)$ and supply $g_1=(10,1)$, with $\eta =0.1$ and $ϵ=0$. Both accumulated entries are positive, so the denominators are defined. The first step givesPlain gradient descent with the same scalar learning rate would instead give $(-1,-0.1)$. If the next supplied gradient is again $(10,1)$, then $s_2=(200,2)$ and each coordinate's additional movement is $-0.1/\sqrt{2}$. These are explicit supplied-gradient calculations, rather than a convergence claim.

In this cumulative version, an accumulated squared-gradient entry never decreases, so its effective coordinate learning rate does not increase. Other adaptive gradient methods retain decaying averages instead, changing how strongly old gradients influence later updates. Adaptation therefore specifies both the state recurrence and how that state transforms the gradient; the word “adaptive” alone does not determine either.

Coupled L2 regularization adds a quadratic parameter penalty to the objective function and sends its gradient through the same optimizer update as the data gradient. With coefficient $\lambda \ge 0$, defineSince the gradient of the squared Euclidean norm divided by two is $\theta$, a supplied data gradient $g=\nabla f(\theta )$ becomesThe factor $1/2$ fixes the convention: a penalty written as $\lambda \Vert \theta {\Vert }_2^2$ instead contributes $2\lambda \theta$.

For plain gradient descent, this substitution givesIt is therefore equivalent to decoupled weight decay with the matched coefficient in this particular update. The equivalence need not survive coordinate-dependent processing of the gradient.^[ref]

For an original fixed-scaling example, let $\theta =(1,1{)}^T$, $g=0$, $\eta =0.1$, $\lambda =0.2$ and diagonal matrix $D=\mathrm{diag}(1,0.1)$. Applying $D$ to the whole coupled gradient givesThe same quadratic penalty produces unequal coordinate shrinkage after this scaling. Uniform decoupled weight decay would instead give $(0.98,0.98{)}^T$. The example isolates a fixed scaling operation, rather than claiming to simulate a complete adaptive gradient method.

Coupling can also change the optimizer state. For example, a momentum buffer formed from $\tilde{g}$ stores contributions from $\lambda \theta$ along with the data gradient. If an adaptive accumulator uses squared gradient entries, it receives $(g_i+\lambda {\theta }_i{)}^2$, including a cross term $2\lambda g_i{\theta }_i$. Subsequent updates can therefore differ even when the next data gradient is the same. State both the penalty convention and the optimizer's gradient-processing rule when describing an L2 setting.

Decoupled weight decay applies a parameter-shrinkage contribution separately from the optimizer's processing of the data gradient. Write $u_t$ for the processed data-gradient direction, including any algorithm-specific optimizer state. Using the coefficient convention documented for PyTorch AdamW,The shrinkage term uses the pre-update parameter and is not inserted into the gradient moments.^[ref]

This differs from coupled L2 regularization, which processes $g_t+\lambda {\theta }_{t-1}$ as a single gradient input. Decoupled weight decay was introduced for adaptive optimization in the AdamW work; the original paper also writes decay coefficients with the learning-rate factor absorbed differently, so its coefficient must be translated before comparing equations.^[ref]

An original limiting case isolates the shrinkage. Suppose the processed direction is zero at every step and $\eta ,\lambda$ are constant. Repeated substitution givesWith $\eta =0.1$, $\lambda =0.2$ and ${\theta }_0=1$, one update gives 0.98 and 50 updates give approximately 0.36417. For varying learning rates, the corresponding factor isThus the same numerical decay coefficient can have a different accumulated effect under a different learning rate schedule. In this zero-direction model, $0<\eta \lambda <1$ gives sign-preserving shrinkage; other factors have different behaviour.

The update order is also part of the definition. For $\theta =1$, $u=2$, $\eta =0.1$ and $\lambda =0.2$, the stated formula gives $0.98-0.20=0.78$. Applying shrinkage after first taking the gradient step would instead give $(1-0.20)0.98=0.784$. Both operations may be described informally as decay plus a step, but they are different recurrences. An optimization checkpoint must retain the relevant state and settings to reproduce the chosen one.

The diagonal AdaGrad accumulator stores a cumulative squared-gradient total for each coordinate:These quantities form part of AdaGrad's optimizer state. An unconstrained diagonal update uses them through a coordinate scale such as $1/(\sqrt{s_{t,i}}+ϵ)$ with a declared positive stabilizer $ϵ$. The accumulator itself and its inverse-square-root transformation are distinct objects.^[ref]

The relation to the full gradient history is exact. Form the sum of outer productsThen $(G_t{)}_{ii}=s_{t,i}$. Retaining only this diagonal is cheaper than retaining every entry of $G_t$, but discards cross-coordinate information.

For an original two-step example, compare historiesBoth give $s_2=(2,2{)}^T$. Their full matrices differ:The diagonal state cannot distinguish those joint gradient patterns. If both are next supplied with $g_3=(1,0{)}^T$, both accumulators become $(3,2{)}^T$ and produce the same coordinate scaling for that update.

Every entry is nonnegative and nondecreasing, since each added square is nonnegative. Alternating gradient signs therefore cannot cancel their contribution to this state. For example, scalar gradients 3 and −3 give accumulated value 18 rather than 0. A saved parameter vector does not reconstruct that history: resuming the same AdaGrad recurrence requires the corresponding accumulator and settings in the optimization checkpoint.

Jimmy Lei Ba, also known as Jimmy Ba, is a computer scientist whose published work includes Adam and layer normalization. His personal research biography identifies Geoffrey Hinton as his doctoral supervisor and describes a focus on efficient algorithms for deep learning.^[ref] The 2016 layer-normalization manuscript prints his University of Toronto affiliation and the name Jimmy Lei Ba.^[ref]

Ba coauthored Adam: A Method for Stochastic Optimization by Diederik P. Kingma and Jimmy Lei Ba with Diederik P. Kingma. The algorithm maintains optimizer state based on gradients, so its update depends on the history of the optimization. Adam bias correction accounts for the early effect of initializing its exponential accumulators at zero.^[ref]

The layer normalization paper, coauthored with Jamie Ryan Kiros and Geoffrey E. Hinton, addresses a different part of a neural network: it computes a mean and variance across feature coordinates of an individual example, then applies learned gain and bias. It avoids making those statistics depend on the other examples in the mini-batch.^[ref]

An original numerical example illustrates one precise symmetry. In the stabilized formula of layer normalization, set all gains to 1, all biases to 0, and layer-normalization epsilon to $\epsilon =1/3$. For $z=(1,2,3)$, the coordinate arithmetic mean is 2 and the coordinate variance is $2/3$, so the normalized output is $(-1,0,1)$. Adding 10 to every coordinate gives $(11,12,13)$, whose output is again $(-1,0,1)$: layer normalization is invariant under a common input shift because the coordinate mean shifts by the same amount and the deviations remain unchanged.

The fixed layer-normalization epsilon affects scaling differently. With $2z=(2,4,6)$, the coordinate variance is $8/3$ and the output is $(-2/\sqrt{3},0,2/\sqrt{3})$, which differs from the original output. This calculation distinguishes the exact common-shift symmetry from idealized scale invariance when the stabilizer is omitted. It does not assign either numerical example to the paper's experiments.

A momentum buffer stores an accumulated history of gradients for an optimization algorithm. In one common convention, a parameter vector ${\theta }_k$, supplied gradient $g_k$, learning rate ${\eta }_k$ and constant coefficient $0\le \mu <1$ obey the recurrence relationThe buffer belongs to the optimizer state: it remembers earlier inputs even when the current parameters are unchanged. This is the undampened momentum convention used by PyTorch stochastic gradient descent with weight decay and the Nesterov accelerated gradient method disabled; its documented first buffer is the first gradient, agreeing with this recurrence from $b_0=0$. Other conventions absorb the learning rate into the stored buffer, so a buffer value needs its update convention to be interpreted.^[ref]

Repeated substitution gives the exponentially weighted gradient historyTo verify this identity, substitute its expression for $b_k$ into $b_{k+1}=\mu b_k+g_k$: multiplication by $\mu$ raises every old exponent by one, and the added $g_k$ is precisely the new exponent-zero term. The formula holds at $k=0$ because its sum is empty, completing the mathematical induction.

For an original scalar example with $b_0=0$ and a constant supplied gradient $g_j=1$, the geometric series yields $b_k=(1-{\mu }^k)/(1-\mu )$. At $\mu =0.9$, $b_{10}\approx 6.5132$ and the limit is 10. The buffer is an unnormalized sum: multiplying it by $1-\mu$ changes its scale, and would require a corresponding learning rate adjustment to preserve these parameter updates.

The same memory explains why momentum can temporarily oppose the current gradient. If $b_k=10$, $\mu =0.9$ and the new scalar gradient is $g_k=-1$, then $b_{k+1}=8$. With a positive learning rate, the parameter still decreases, although the present negative gradient alone would call for an increase. Persistence can carry motion through rapidly alternating gradients, but this example also shows why the rule need not decrease the objective function at every step.

An optimization checkpoint is a saved description of an ongoing optimization algorithm from which its optimizer updates can resume. It combines the current parameters with the relevant optimizer state. The practical criterion is optimizer restart equivalence: after restoring the saved information and supplying the same subsequent inputs, the chosen update rule should produce the same subsequent states.

For a deterministic scalar example, minimize the quadratic function $f(\theta )={\theta }^2/2$ with gradient $g_k={\theta }_k$, learning rate $\eta =0.1$ and momentum buffer recurrence $b_{k+1}=0.9b_k+g_k$, followed by ${\theta }_{k+1}={\theta }_k-0.1b_{k+1}$. Start with $({\theta }_0,b_0)=(1,0)$. After one step the saved pair is $({\theta }_1,b_1)=(0.9,1)$. Restoring both gives $b_2=1.8$ and ${\theta }_2=0.72$. Restoring only ${\theta }_1$ and initializing a new momentum buffer to zero gives $b_2=0.9$ and ${\theta }_2=0.81$. Equal saved parameters can therefore lead to unequal continuations. These numbers are an original calculation for the declared recurrence.

In PyTorch, a general training checkpoint commonly serializes separate model and optimizer dictionaries, together with the training position. The model dictionary contains learned parameters and registered model buffers; the optimizer dictionary contains its own changing state and group settings.^[ref] Restoring the optimizer state-to-parameter association also matters: the optimizer loader pairs stored identifiers with parameters in group order, without independently establishing that they denote the same mathematical parameters.^[ref]

The required checkpoint boundary depends on the computation being resumed. A changing learning rate schedule, the next position in the training data, and the state of a pseudorandom number generator can influence future updates. Matching them is part of computational reproducibility; a saved parameter vector alone does not specify the whole training process.

The optimizer state is information retained by an optimization algorithm beyond the current parameter values. It can include a momentum buffer and algorithm-specific counters or running estimates. Consequently, two runs with identical parameters and current gradients can produce different next optimizer updates if their stored states differ.

For an original scalar example, minimize $f(\theta )={\theta }^2/2$ with the recurrenceThis is the momentum form with dampening, decay and the nesterov flag disabled in the PyTorch stochastic gradient descent implementation.^[ref] At ${\theta }_k=1$, $\eta =0.1$ and $\mu =0.9$, a stored $b_k=0$ gives $b_{k+1}=1$ and ${\theta }_{k+1}=0.9$. A stored $b_k=2$ instead gives $b_{k+1}=2.8$ and ${\theta }_{k+1}=0.72$. The current parameter and gradient were identical; the difference came from history.

An optimization checkpoint that saves only the parameters cannot reproduce that next step. In PyTorch, Optimizer.state_dict() stores per-parameter state and parameter-group settings such as learning rate, but not the parameter values themselves. Its parameter identifiers associate state with ordered parameter groups and are not a check of semantic parameter identity during loading.^[ref] Save and restore the corresponding parameters separately and keep the state-to-parameter association consistent. Reproducing an entire training run may additionally require the data order and other changing state.

Optimizer state-to-parameter association identifies which parameter each saved piece of optimizer state belongs to. An optimization checkpoint can contain every stored number and still resume incorrectly if those numbers are attached to different parameters. Equal shapes and data types do not establish mathematical identity.

The PyTorch optimizer dictionary separates per-parameter state from parameter-group settings. Its loader pairs saved parameter identifiers with the current parameters in group order, without independently verifying the intended association.^[ref]

For an original two-parameter example, use $b^{\prime }=0.5b+g$ and ${\theta }^{\prime }=\theta -0.1b^{\prime }$. Let the named parameters be $a=1$ and $c=10$, their current gradients both be 1, and their saved momentum buffers be $b_a=2$ and $b_c=20$. Correct restoration givesIf a reversed parameter ordering attaches the same saved buffers to the wrong scalar parameters, the result is insteadBoth buffers had valid scalar shapes, so a shape check would not expose this error.

Consistently permuting the parameters, gradients and state is merely a change of ordering; permuting only the state changes the algorithm's continuation. Record a stable parameter schema and group order with the checkpoint, and check any intentional remapping against that schema. Parameter values and optimizer dictionaries are distinct saved objects, so restoring one does not automatically restore the other's meaning.^[ref]

An optimizer update changes the adjustable parameters of an optimization problem according to an algorithm's current information. Evaluating a loss function, computing its gradient and changing the parameters are distinct operations. A general update may also change an optimizer state, such as stored information from previous steps:Here $g_k$ is the supplied gradient and ${\eta }_k$ a learning rate. The PyTorch interface makes this separation explicit with gradient computation followed by optimizer.step().^[ref]

For plain gradient descent with no extra state, ${\theta }_{k+1}={\theta }_k-\eta g_k$. In an original scalar example, choose $f(\theta )={\theta }^2/2$, ${\theta }_0=2$ and $\eta =0.1$. The gradient is 2, so the update gives ${\theta }_1=1.8$ and lowers the loss from 2 to 1.62. Recompute the gradient at the new parameter value to obtain ${\theta }_2=1.62$. Reusing the old gradient 2 instead would give 1.6. This explicitly locates where the algorithm obtains its information.^[ref]

An update is not automatically an improvement: using $\eta =3$ for the first step above gives ${\theta }_1=-4$ and loss 8. With gradient accumulation, several gradient calculations instead contribute before a single optimizer update; their weighting sets the effective batch size. Track the update count separately from the number of processed groups, particularly when applying a learning rate schedule.

SGDR means stochastic gradient descent with warm restarts. Its learning rate schedule repeatedly lowers the learning rate along a cosine curve, then raises it to begin another cycle while retaining the current parameters. Ilya Loshchilov and Frank Hutter's method uses this warm restart to continue an existing optimization trajectory.^[ref]

In cycle $i$, let $s$ be elapsed training time since the last restart and $T_i>0$ the cycle duration, measured in the same units. The cosine learning rate schedule isIt starts at ${\eta }_{\max ,i}$, reaches the midpoint of the two bounds at $s=T_i/2$, and reaches ${\eta }_{\min ,i}$ at the cycle endpoint. The original implementation updates the elapsed training epoch count within each mini-batch, allowing fractional epoch progress.^[ref]

For an original schedule, choose bounds 0 and 0.1, initial duration $T_0=4$ epochs and duration multiplier 2. The successive cycle lengths are 4, 8 and 16 epochs, with restart boundaries at total elapsed times 4, 12 and 28. In the first continuous cycle, the rates at $s=0,2,4$ are respectively $0.1,0.05,0$.

A discrete convention must specify which update uses the endpoint. For example, sampling phases $s=0,1,2,3$ in the first cycle and restarting before the next step gives rates approximately $0.1,0.08536,0.05,0.01464$, followed by $0.1$. The zero endpoint in the continuous curve is then a limit, rather than an additional zero-rate optimizer step.

Retaining parameters also has a concrete meaning. In an original deterministic gradient descent example with $f(\theta )={\theta }^2/2$ and current $\theta =0.5$, resetting only the schedule leaves $\theta =0.5$. The next step at learning rate0.1 gives0.45; a step at0.01 would give0.495. The restart changes the next movement rather than drawing a new initial parameter. Handling a momentum buffer is a further state convention; restarting the schedule and discarding all optimizer state are different operations. Record cycle phase, durations and rate bounds with an optimization checkpoint.

A warm restart continues an optimization process from an already obtained solution while restarting specified algorithm controls or history. Its meaning depends on which fields are retained. In SGDR, the current parameters are retained while the learning rate schedule starts another cycle; the original paper explicitly distinguishes this from starting the optimization from scratch.^[ref]

Write a complete algorithm state as $(\theta ,s,c)$, where $\theta$ holds parameters, $s$ is optimizer state and $c$ holds controls such as the schedule phase. A restart map can retain $\theta$ while replacing $c$, or can also replace selected parts of $s$. Saying only “restart” does not specify the next optimizer update.

For an original scalar example, take $f(\theta )={\theta }^2/2$ and the momentum buffer recurrenceAt current $\theta =2$, stored $b=-4$, $\mu =1/2$ and restarted learning rate $\eta =0.1$, retaining the buffer givesRetaining the same parameters but resetting the buffer to zero gives $b^{+}=2$ and ${\theta }^{+}=1.8$. Both runs start the next update at $\theta =2$; they differ in the history carried through the restart.

A schedule-only restart can also change the next step without changing stored parameters immediately. In a plain gradient descent update from $\theta =2$, increasing the learning rate from 0.01 to 0.1 changes the next value from 1.98 to 1.8. The change takes effect through the subsequent gradient step.

An optimization checkpoint instead records enough information to reproduce a specified continuation. A deliberate warm restart may intentionally alter some of that information. Record the retained parameter state, the new schedule phase and the policy for buffers or counters before comparing trajectories or claiming optimizer restart equivalence.

Weight decay supplies a parameter-shrinkage contribution to an optimizer update, with a coefficient commonly denoted $\lambda$. Two implementations must be distinguished. Coupled L2 regularization adds the penalty $\lambda \Vert \theta {\Vert }^2/2$ to the objective function, replacing its data gradient $g$ by $g+\lambda \theta$. Decoupled weight decay applies parameter shrinkage separately from the optimizer's processing of the data gradient. These operations are equivalent for plain gradient descent with matched coefficients, but not in general for an adaptive gradient method.^[ref]

Use the PyTorch convention here: a decoupled update shrinks parameters by $1-\eta \lambda$, where $\eta$ is the learning rate. A source writing $1-\lambda$ instead has absorbed the step-size factor into its decay coefficient. For an unmodified gradient step,In AdamW, the decay contribution does not enter the stored first- or second-moment estimates of the gradient.^[ref]

An original fixed-scaling example exposes the difference. Let $\theta =(2,2{)}^T$, $g=(1,1{)}^T$, $\eta =0.1$, $\lambda =0.2$ and diagonal matrix $A=\mathrm{diag}(1,10)$. Applying the same scaling to the entire coupled gradient givesSeparating uniform parameter shrinkage givesThe second coordinate receives different shrinkage. This is an illustrative fixed matrix, not a full AdamW simulation. With history-dependent scaling, coupling the penalty into the gradient can also alter the optimizer state. State the update equation and coefficient convention when reporting a decay setting; the label alone does not specify either.

Yoram Singer coauthored the 2011 AdaGrad paper with John Duchi and Elad Hazan. Their adaptive gradient methods use past subgradients to change the geometry of later optimizer updates.^[ref]

An unconstrained diagonal specialization uses a diagonal AdaGrad accumulatorwith learning rate $\eta >0$ and stabilization $\delta >0$ outside the square root. The accumulator is part of the optimizer state.^[ref]

For an original supplied-gradient example, let the current accumulator be $s_t=(100,1)$, the current gradient be $g_t=(1,1)$, and choose $\eta =0.1$, $\delta =1$. These accumulator values include the current gradient. The next displacement isThe identical current gradient coordinates produce different movements because their histories differ. Plain gradient descent with the same learning rate would move by $(-0.1,-0.1)$. This calculation exposes the mechanism without asserting that either update improves every possible objective function.

The example also explains why saving only the parameter vector is insufficient to reproduce a later adaptive step. Two runs at the same $x_t$, receiving the same $g_t$, can move differently if their stored accumulators differ.